cs.LG · 2026-07-19 · No. 58
Machine Learning, 2026-07-19.
53 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
53 entries-
01
Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier
Arthur G. Bubolz, Abreu Quevedo, Giancarlo Lucca, Rafael A. Berri, Eduardo Borges, Bruno L. Dalmazo
cs.LG · cs.CE
The growing use of Bitcoin as a decentralized digital asset and investment tool has sparked strong interest in understanding its market behavior. This study presents a new approach to analyze Bitcoin market sentiment by combining on-chain and financial data with social media posts. Unlike models that aim to predict prices, this work focuses on explaining market sentiment using blockchain transactions, historical price data of Bitcoin, and...
-
02
Mutable Low-Rank Sketches for Retrain-Free Recommendation
Hector J. Garcia, Nick Clayton
cs.LG
A common bottleneck in two-stage recommendation is embedding staleness: when a user rates a new item, their embedding remains fixed until the next retrain cycle. We propose mutable sketches, which store each user's preferences in a KP-tree (a sparse segment tree with sum aggregation), fit a low-rank projection once, and recompute embeddings on-the-fly as ratings arrive. We prove that each new observation monotonically tightens the prediction...
-
03
Data Driven Block Replacement Scheduling
Aniruddhan Ganesaraman, VIdyadhar Kulkarni
cs.LG · math.OC · stat.AP · stat.ML
We develop data-driven algorithms for maintaining $N$ independent identical machines under a \textit{block replacement policy}, in which each machine is replaced upon failure and all machines are jointly replaced at regular intervals of length $k$. The goal is to learn the cost-minimizing interval $k^*$ from operational data when the lifetime distribution is unknown. At each decision epoch, the operator selects $k \in \{1, 2, \ldots, K\}$,...
-
04
BadWAM: When World-Action Models Dream Right but Act Wrong
Qi Li, Xingyi Yang, Xinchao Wang
cs.LG · cs.RO
World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction. This coupling is often viewed as a source of robustness, interpretability, and safety, as a robot's action can in principle be checked against its imagined future. In this paper, we show that this assumption is fragile. We introduce...
-
05
RTS Smoother-Guided Learning of Physics-Based Neural Differential Models
Ahmet Demirkaya, Georgios Stratis, Tales Imbiriba, Zachary D. Danziger, Deniz Erdogmus
cs.LG · eess.SY
Ordinary differential equations (ODEs) are widely used to model dynamical systems in physics, biology, neuroscience, and physiology, but in many applications some equations of the dynamics are unknown and only a subset of the state variables are measured. We propose a hybrid neural--physics framework in which the known components of the ODE are kept explicit and the missing components are represented by a neural network. The proposed method...
-
06
On-Policy Delta Distillation
Byeongho Heo, Jaehui Hwang, Sangdoo Yun, Dongyoon Han
cs.LG · cs.CL
On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model. Although on-policy distillation has been studied and applied across various settings, its fundamental design remains underexplored. In this paper, we introduce a new distillation reward, termed the delta signal, instead of directly imitating...
-
07
Learning in Infinitesimal Non-Compositional Sketches
Sridhar Mahadevan
cs.LG · math.CT
This paper develops a categorical framework -- Learning in Infinitesimal Non-Compositional Sketches (LINCS) -- as the repair of non-compositionality: failures of diagrams to factor through quotient sketches lifted to the tangent category setting. Machine learning problems are specified as sketches: graphs with commutativity conditions $\mathcal D$, limit cones $\mathcal L$, and colimit cocones $\mathcal K$, generalizing the usual...
-
08
Evaluating covariate balance for long time horizon Markov decision processes
Joshua Spear, Rebecca Pope, Neil J Sebire
cs.LG
This article explores the application of covariate balance diagnostics for detecting the presence of hidden confounding/model miss-specification in studies applying offline reinforcement learning (RL) to deriving optimal treatment recommendations. The results demonstrate that, either there is a high risk of bias within existing offline RL studies for treatment recommendations or, existing covariate balance metrics are not sufficient to assess...
-
09
An Introduction to Sparse Identification of Nonlinear Dynamics for Engineering Applications
Yao Cheng Li, Ana Larrañaga, Steven L. Brunton, Urban Fasel
cs.LG
Many engineering problems involve phenomena whose governing equations are poorly characterized or only partially known. Surrogate modeling techniques such as neural networks can capture the behavior of these systems, but they typically demand large training datasets that are difficult to obtain in engineering contexts and yield models with limited physical interpretability. The Sparse Identification of Nonlinear Dynamics (SINDy) method...
-
10
Kernel weighted importance sampling for off-policy evaluation in contextual bandits
Joshua Spear, Matthieu Komorowski, Rebecca Pope, Neil J Sebire, Erica E. M. Moodie
cs.LG
This article presents a novel estimator for performing off-policy evaluation using only offline data for contextual bandits. The proposed estimator, Kernel-WIS is demonstrated to be asymptotically consistent and to empirically outperform strong baselines (including vanilla weighted importance sampling), particularly under complex conditions including behaviour policy miss-specification. The benefit of Kernel-WIS is derived from combining the...
-
11
Multimodal Semantic-Aware Contrastive Learning For False Negative Mitigation in 3D Medical Imaging
Sara Ketabi, Matthias W. Wagner, Cynthia Hawkins, Uri Tabori, Birgit Betina Ertl-Wagner, Farzad Khalvati
cs.LG · q-bio.QM
Multimodal Contrastive Learning (CL) has shown significant performance in aligning representations across various data modalities and improving downstream tasks, especially in healthcare. It works by minimizing the distance between matched (positive) data modalities, while maximizing the distance between mismatched (negative) samples. Traditional CL frameworks typically assume instance-based correspondence within data batches, treating all...
-
12
Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
Ku Onoda, Paavo Parmas, Hiroki Furuta, Soichiro Nishimori, Yuta Oshima, Shohei Taniguchi, Yutaka Matsuo
cs.LG · cs.AI · cs.CV
Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. This limits the diversity of images, and for person-centric prompts, can reflect or amplify demographic skew. We formalize this problem as coverage of a predefined set of semantically specified modes, which we call target-mode coverage. We then propose multi-axis...
-
13
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Changhai Zhou, Kieran Liu, Yuhua Zhou, Qian Qiao, Jun Gao, Harry Zhang, Irvine Lu, Nolan Ho, Lucian Li, Andrew Lei,...
cs.LG · cs.DC
A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment. The gap is especially important for AI agents, whose observations, tool outputs, documents, and prior decisions accumulate over long trajectories. LongStraw is an architecture-aware execution stack...
-
14
Causal Inference for Sequential Settings under Interference and Latent Confounding
Phevos Paschalidis, Constantinos Daskalakis, Devavrat Shah
cs.LG · math.PR
We study causal inference under outcome interference for sequential, observational settings. Specifically, we consider settings where the binary outcomes over N units are Markovian across T time steps. At each time step, the outcomes of N units have dependencies captured through an Ising model; each outcome is also impacted through an external field capturing the effects of its treatment as well as latent confounders. Similar to panel data...
-
15
A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
Christoph Jürgen Hemmer, Florian Plaswig, Daniel Durstewitz
cs.LG · cs.AI · math.DS · nlin.CD
Recent foundation models (FMs) for zero-shot reconstruction of dynamical systems (DS) achieve strong out-of-domain generalization but provide little insight into the mechanisms that underlie their forecasts. Such an understanding could help to strip down overladen FM architectures to their bare essence and expose the minimal requirements for in-context learning in the DS domain. Toward this goal, here we iteratively reduce a recent powerful...
-
16
Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh
cs.LG · cs.AI · cs.CR
Machine learning models are increasingly adapted in various domains. However, adversarial examples pose a significant threat to the reliable deployment of these models. In recent years, some powerful adversarial example attacks have been proposed for the fast and query-efficient generation of adversarial examples, even in black-box scenarios, highlighting the need for scalable, low-cost, and powerful defenses. In this work, we present two...
-
17
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Yu-Du Feng, Niels Mündler-Sasahara, Mark Vero, Martin Vechev
cs.LG · cs.CL
Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding. These domains permit reliable verification of model outputs, which is important for enabling the reinforcement learning that drives RLM performance gains. However, training RLMs on domains that lack reliable verifiers remains challenging. Meanwhile, for both verifiable and unverifiable domains, large amounts of unused...
-
18
Analytical study of the optimal combination of binary classifiers based on classifiers-induced partitioning of the training set
Jean-Marc Brossier, Olivier Lafitte
cs.LG
This paper studies an optimal linear combination of binary classifiers based on a logical structuration of the dataset via truth tables. The given classifiers partition data into equivalence classes, allowing for a rigorous analysis of the convexified empirical risk through a multidimensional generalization of classification calibrated functions. We establish sufficient conditions for the existence and uniqueness of the (global) point of...
-
19
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
Robert Graham, Edward Stevinson, Yariv Barsheshat
cs.LG · cs.AI · cs.CL · cs.CY
Finetuning language models on small, curated datasets is standard practice for adapting them to specific policies or domains. We show that finetuning on narrow, factually-defensible, moderation-passing data can cause broad ideological shifts across unrelated domains, while preserving general capabilities. Training GPT-4.1 on right- or left-leaning economics Q&A yields matched ideological shifts on topics such as criminal justice, the...
-
20
PAC Learning in Turn-Based Stochastic Games with Reachability Objectives: A Decentralized Private Approach via Expected Conditional Distance
Ali Asadi, Krishnendu Chatterjee, Pavol Kebis
cs.LG · cs.GT
Reachability is the most fundamental logical objective, yet it is notoriously difficult to learn in reinforcement learning settings: even for Markov decision processes, PAC learning of reachability is impossible without additional assumptions. This difficulty also holds in turn-based stochastic games (TBSGs), where two adversarial players interact on a finite state space. In this work, we consider turn-based stochastic games with reachability...
-
21
Asymmetric Peak-Aware Loss for Peak-Critical Time Series Forecasting
Theivaprakasham Hari, Yanan Xin, Winnie Daamen, Serge Paul Hoogendoorn, Sascha Hoogendoorn-Lanser
cs.LG · cs.AI
In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction. Accurate prediction of rare demand spikes plays a critical role in downstream tasks. Yet most time-series forecasters are trained with symmetric objectives (e.g., MSE, MAE) and evaluated primarily on aggregate error, which can mask failures in extreme-values and...
-
22
Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
Jakub Paplhám, Willem Waegeman, Eyke Hüllermeier, Vojtěch Franc
cs.LG · cs.AI
Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning. However, the Bayes-optimal decision strategies for these tasks do not coincide with the scores commonly used to quantify epistemic uncertainty. Building on the epistemic reject-option framework, we evaluate epistemic uncertainty using its ability to identify regret, the reducible error. Formulating selective prediction as a...
-
23
ChronoQG: Towards a Temporally Expressive and Hop-Bounded Benchmark for Temporal Knowledge Graph Question Generation
Xuemeng Liu, Zhengpin Li, Wanpeng Tang, Haotong Xie, Wentao Zhang
cs.LG
Knowledge graph question generation (KGQG) aims to generate natural-language questions from structured graph evidence. Existing KGQG benchmarks, however, are mostly built on static knowledge graphs and do not encode the temporal scopes of graph facts. As a result, they cannot evaluate whether generated questions faithfully preserve temporal validity, event ordering, and answer-determining temporal constraints. In this paper, we study temporal...
-
24
GAttNHP: Group Attention Neural Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs
Xiangni Tian, Kaixian Yu, Runpeng Dai, Niansheng Tang, Hongtu Zhu
cs.LG · stat.ML
Temporal Knowledge Graphs (TKGs) record how facts evolve over time, but forecasting future events on a TKG remains difficult for three reasons: (i) long-range temporal dependencies are hard to encode; (ii) events on different chains mutually excite or inhibit one another in ways that snapshot-level models cannot express; and (iii) inter-arrival times are heavy-tailed and statistically sparse, so deterministic time predictors are unreliable....
-
25
What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity
Kumar Kshitij Patel, Rustem Islamov, Sebastian U Stich, Aurelien Lucchi, Eduard Gorbunov, Lingxiao Wang
cs.LG · math.OC · stat.ML
Local SGD, also known as Federated Averaging, is a widely used distributed optimization algorithm. Although Local SGD often outperforms alternatives such as Mini-batch SGD in practice, theory still only partially explains when and why local updates help under realistic data heterogeneity. Recent work by [Patel et al., 2025] shows that a bounded second-order heterogeneity assumption captures the efficiency of Local SGD for strongly convex...
-
26
Counterfactuals for Feature-Weighted Clustering
Richard J. Fawley, Renato Cordeiro de Amorim
cs.LG
Counterfactual explanations provide local, interpretable insight by identifying changes to an input that would alter its assigned outcome. Although well established in supervised learning, their extension to clustering is less direct, since cluster assignments are unlabeled and governed by the geometry of the partition. This paper introduces VoICE, a Voronoi-Induced Counterfactual Explainability framework for feature-weighted $k$-means...
-
27
MESHA: Mechanism-Enforced Sequential Halving for Strategic Linear Bandits
Xin Li, Zixin Zhong
cs.LG
We design and analyze \underline{M}echanism-\underline{E}nforced \underline{S}equential \underline{HA}lving (MESHA), an algorithm for Best Arm Identification (BAI) in strategic linear bandits. In this setting, each arm may strategically misreport its feature vector to maximize the probability of being identified as the best arm, when rewards are generated from the arms' true but unobservable features. The design of MESHA applies the naïve...
-
28
Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics
Yuchang Zhu, Zezhong Xie, Huizhe Zhang, Huazhen Zhong, Jintang Li, Liang Chen, Zibin Zheng
cs.LG
Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race. While this challenge has motivated extensive research, most existing solutions rely on the strong assumption that demographics are fully available. To bypass this strict requirement, a few recent studies have attempted to use predicted...
-
29
Scalable Training of Continuous-Time Spiking Neural Networks with Differentiable Spike-Time Discretization
Yusuke Sakemi, Tomoya Takeuchi, Takeo Hosomi, Kazuyuki Aihara
cs.LG
Continuous-time spiking neural networks (SNNs) provide an event-driven framework for temporal computation, computational neuroscience, and neuromorphic hardware. However, training deep continuous-time SNNs is severely constrained by the memory required for exact spike-time computation, which evaluates and retains candidate firing times over intervals determined by presynaptic spike ordering. Here we introduce a memory-efficient training...
-
30
Trajectory-Aware Flow Matching for Topology Optimisation
Shusheng Xiao, Jinshuai Bai, Hyogu Jeong, Yunfei Xi, Yilin Gui, YuanTong Gu
cs.LG · math.NA
Topology optimisation (TO) often requires repeated finite element analysis and sensitivity-based material updates, which can be costly when multiple candidate designs are needed under varying physical and design conditions. Generative TO offers a route to rapid design exploration, but existing models may rely on adversarial training, long reverse-diffusion sampling, or external guidance to maintain structural feasibility and physical...
-
31
TIDE: Trustworthy and Interpretable Battery Degradation Estimation with Contextual Learning and Symbolic Distillation
Wen Yang Tan, Jiawei Li, Fang Liu, Wei Zhang, Sumei Sun, Peng Cheng Wang, Elisa Y. M. Ang
cs.LG
Battery health estimation is fundamental for battery management in battery-powered systems, where inaccurate health states may affect control, maintenance, and service life. It becomes even more critical in intelligent connected systems, where estimation errors can propagate across interconnected devices and downstream decisions. In this paper, we propose TIDE, a trustworthy and interpretable battery degradation estimator for reliable battery...
-
32
PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference
Hyunwoo Oh, Suyeon Jang, Hanning Chen, KyungIn Nam, Sanggeon Yun, Ryozo Masukawa, Mohsen Imani
cs.LG · cs.AR · cs.OS
CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained mixed precision that is difficult to execute efficiently on CPUs. We present PolyQ, a CPU-oriented compiler/quantization co-design for activation-aware channel-wise bit allocation under a user-specified average-bit budget. PolyQ assigns per-channel bit-widths from $\{2,3,4,8,16\}$, then...
-
33
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
Weiwen Xu, Jia Liu, Hou Pong Chan, Long Li, Deng Cai, Min Chen, Hao Zhang
cs.LG · cs.AI · cs.CL
Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion, limiting its effectiveness as a correctness signal. We propose Contrastive Policy Optimization (CPO), which uses token-level contrastive disagreement between reference-guided and vanilla generation distributions for correctness-aware advantage shaping. Both...
-
34
Angular Gaussian Supervised Contrastive Learning for Long-Tailed Electrocardiogram Arrhythmia Diagnosis
Jin Dai, Qiuzhen Zhang, Chenyun Dai, Danmei Lan, Can Han
cs.LG · cs.AI
Long-tailed label distributions reduce the reliability of deep learning for electrocardiogram (ECG) arrhythmia diagnosis, particularly for clinically important but rare abnormalities. Existing rebalancing and logit adjustment methods mainly address class frequency while overlooking direction-dependent morphological variability across ECG classes. This study proposes Angular Gaussian Supervised Contrastive Learning (AG-SCL) for long-tailed...
-
35
Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms
Umid Suleymanov, Ilhama Novruzova, Khalid Mammadov, Natavan Hasanova, Murat Kantarcioglu
cs.LG · cs.AI
Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees. While prior work has largely examined how privacy-preserving techniques affect fairness, the inverse question-how fairness-enhancing algorithms influence privacy leakage-remains underexplored. We present the first comprehensive study of how fairness...
-
36
Accelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap
Olivier Jeunen
cs.LG · cs.IR · stat.ME
Online controlled experiments are the gold standard for hypothesis testing in online platforms. Notwithstanding their ubiquity, they are notoriously expensive to run, and issues of variance hamper statistical power in assessing treatment effects. While standard variance reduction techniques leverage model-based control variates to reduce outcome noise, they remain agnostic to potential structural relationships between competing policies. In...
-
37
Sharp Stability Threshold and Certification for Designing Stable Residual Architectures
Hyemin Gu, Michael Tyrrell, Tuhin Sahai, Markos A. Katsoulakis
cs.LG · stat.ML
We propose \emph{the sublinear-growth principle} for deep residual architectures -- a sharp stability threshold on the input-magnitude exponent of every residual block's velocity field: $$\|v(x, t)\| \leq c\,\|x\|^q + b, \qquad q \in [0, 1].$$ The threshold $q = 1$ is established via two independent arguments. Classical ODE theory gives a global forward flow on $[0, T]$ at $q \le 1$ and exhibits divergent velocity fields at any $q > 1$. The...
-
38
Gate-Zero Growth: A Geometric Framework for Function-Preserving Continual Learning
Dante Lok
cs.LG · cs.AI
We introduce \emph{gate-zero growth}, a function-preserving (FP) operator for continual learning that adds new residual blocks through a zero-initialised gate. Under a transversality condition, gate-zero growth induces \emph{rank separation} in the functional Jacobian: old directions are unchanged, new-weight directions are exactly flat at the growth point, and new gate directions are the only first-order source of new functional variation....
-
39
Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data
Tatthapong Srikitrungruang, Jaesung Lee
cs.LG · stat.ML
Estimating spatially heterogeneous elastic properties from low-resolution displacement measurements is a severely ill-posed inverse elasticity problem because low resolution obscures spatial details needed to distinguish heterogeneous property variations, and small measurement perturbations or fitting errors are amplified through inverse estimation. Existing inverse methods often rely on high-fidelity observations and manually prespecified...
-
40
CASP: Learning-Augmented Offline Approximation with Verifiable Certificates and Bounded-Loss PAC Guarantees
Haifeng Li, Mo Hai
cs.LG
Machine-learned predictions can speed up offline NP-hard optimization, but asking a predictor what to do amounts to asking it to solve the problem, and committing an unchecked prediction forfeits every worst-case guarantee. CASP (Certificate-Augmented Solution Pruning) instead asks which parts of the search space may be ignored, and accepts each answer only after a sound polynomial-time verifier has checked it, so correctness never depends on...
-
41
Muse: Representation Geometry of Muon Beyond Normalized Momentum
Da Chang, Qiankun Shi, Lvgang Zhang, Di He, Yaoshuai Ma, Ganzhao Yuan, Yongxiang Liu
cs.LG
Muon-style optimizers apply a polar map to matrix momentum, but their updates also depend on the representation of each parameter block before orthogonalization. We study this representation choice as a form of optimizer geometry and introduce {\method}, a family of Muon-style optimizers that shares the same momentum rule and Newton--Schulz backend across native, nearest-square, skinny, and vector representations. Each Frobenius-isometric...
-
42
xHC: Expanded Hyper-Connections
Xiangdong Zhang, Xiaohan Qin, Sunan Zou, Tuo Dai, Xiaoming Shi, Huaijin Wu, Yebin Yang, Zhuo Xia, Shaofeng Zhang,...
cs.LG · cs.CL
Hyper-Connections (HC) expand the residual stream of Transformers into $N$ parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained HC (mHC) stabilizes this formulation at scale. The large gains from $N{=}1$ to $N{=}4$ suggest residual-stream expansion as a promising scaling axis. However, existing HC-family methods typically stop at $N{=}4$. Our experiments reveal why: scaling mHC beyond this...
-
43
A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models
Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang
cs.LG
We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive the corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy...
-
44
Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers
Akhilesh Gogikar
cs.LG · math.OC · stat.ML
Interpreting optimizers as gradient-flow discretizations has motivated applying higher-order Runge-Kutta (RK) integrators to neural networks. We build a representative Adam variant (Bogacki-Shampine 3(2) RK pair, FSAL reuse, local-error step control) and evaluate it under a strict compute-matched protocol giving every method the same gradient-evaluation budget - an accounting this literature rarely enforces. Under it the RK variant loses to...
-
45
Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards
Yuxuan Zhu, Rohan Alur, Daniel Kang
cs.LG · cs.AI
While reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capabilities of large language models (LLMs), the generalizability of the resulting models remains poorly understood. In this work, we establish the first non-vacuous generalization bounds for parameter-efficient RLVR fine-tuning at the billion-parameter scale. Our approach adapts PAC-Bayes compression bounds to this setting, and addresses the...
-
46
Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance
Matt L. Wiemann, Peter Melchior, Andrew K. Saydjari
cs.LG
Noise injection is a well-known technique in stochastic optimization. We report its surprising effectiveness with an interleaved (on-off-on-off...) rather than the usual monotonic decay schedule. We present a theoretical analysis of noise injection, which confirms that corruption by impulse noise approximates a Jacobian regularization, whereas Gaussian noise acts as a curvature penalty. This regularization behavior has been invoked to explain...
-
47
Depth-Dependent Hidden-State Collapse in Dynamical System Autoencoders for LiDAR Point-Cloud Classification
Patricia Medina, Hy P. G. Lam
cs.LG · cs.CV
We study Dynamical System Autoencoders (DSAE) for LiDAR point-cloud classification using spatial coordinates and Product Coefficient feature augmentations. The experiments compare separately trained DSAE architectures at encoder depths $K=1,\ldots,5$ and evaluate the resulting hidden representations with Random Forest, kNN, and a majority-class Dummy baseline. The main finding is a hidden-state collapse at $K=5$. For both xyz and xyz plus...
-
48
Active Real-World Factor-Based Evaluation for Generalist Robot Policies
Andrew Liao, Hanchen Cui, Karthik Desingh, Aryan Deshwal
cs.LG · cs.RO
Generalist robot manipulation policies trained on large, diverse datasets have shown remarkable promise across a wide range of tasks. However, rigorously evaluating these policies remains a fundamental challenge. Real-world performance depends on a large combinatorial space of task factors including object poses and camera viewpoints, making full, exhaustive evaluation intractable. Additionally, real hardware evaluation is slow and...
-
49
HyperShadow: A Benchmark for Detecting 3D Projections of Higher-Dimensional Spatial Objects
Akshay Sasi
cs.LG · cs.CG
Machine-learning datasets labelled "4D" universally denote three spatial dimensions plus time. We introduce HyperShadow, the first public benchmark in which the fourth, fifth, and sixth dimensions are spatial: the task is to decide whether a 3D point cloud is a native three-dimensional shape or the projection, the "shadow", of a rigid object living in R^N (N = 4-6). We show this task is fundamentally distinct from intrinsic-dimension...
-
50
Adaptive Ad Load Design for Sponsored Search Markets: Evidence, Theory, and Deployment
Mohammad Rashid, Hema Yoganarasimhan
cs.LG · econ.GN
Ad-load design is a central supply-side decision in sponsored search: more sponsored slots can raise revenue, but may crowd out organic results and degrade user outcomes. We study this trade-off using a large-scale randomized field experiment on an Android app store, where over five million users are exposed to one through six sponsored slots. Increasing ad load raises revenue by up to 43%, but reduces total search conversions by up to 5% and...
-
51
LATTICE: Graph Self-Supervised Learning for Multimodal Spatial Omics Integration
Jagan Mohan Reddy Dwarampudi, Veena Kochat, Suresh Satpati, Kunal Rai, Tania Banerjee
cs.LG · q-bio.GN
Spatially resolved omics studies increasingly combine transcriptomic and epigenomic assays, yet downstream analysis is often still performed using single-modality pipelines. We present LATTICE (Latent Alignment of Tissue-level and Transcriptomic Information for Cross-modal Embedding), a graph-based self-supervised framework that learns spot-level representations from harmonized multimodal features. LATTICE integrates five aligned modality...
-
52
Integration Matters: Rollout-Based Training for Constrained Diffusion Models
Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg, Frank Wood
cs.LG · cs.AI
Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during...
-
53
A Noise-Robust Elicit-to-Optimize Framework for Distortion Riskmetrics via Inverse Reinforcement Learning
Yang Liu, Yuhao Liu, Yunran Wei
cs.LG · q-fin.RM
We propose a noise-robust elicit-to-optimize framework that integrates inverse reinforcement learning (IRL) and reinforcement learning (RL) for eliciting agents' risk preferences and optimizing policies under a broad class of risk objectives characterized by distortion riskmetrics. On the elicitation side, we propose an adaptive Bayesian IRL method that infers agents' latent risk objectives from their noisy observed decisions, explicitly...
This edition is part of The Daily Abstract — cs.LG archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.