- An Approximate Ascent Approach To Prove Convergence of PPO
Leif Doering, Daniel Schmidt, Moritz Melcher, Sebastian Kassing, Benedikt Wille, Tilman Aach, Simon Weissmann
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- Universal Costas Matrices: Towards a General Framework for Costas Array Construction
Fatih Gulec, Vahid Abolghasemi
arXivSource: arxiv.orgFeb 3, 2026cs.ITscore 0
- Soft-Radial Projection for Constrained End-to-End Learning
Philipp J. Schneider, Daniel Kuhn
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems
Ronald Katende
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- Sparse Training of Neural Networks based on Multilevel Mirror Descent
Yannick Lunk, Sebastian J. Scott, Leon Bungert
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- Riemannian Neural Optimal Transport
Alessandro Micheli, Yueqi Cao, Anthea Monod, Samir Bhatt
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- Sleep or Transmit: Dual-Mode Energy-Efficient Design for NOMA-Enabled Backscatter Networks
Hajar El Hassani, Mikael Gidlund
arXivSource: arxiv.orgFeb 3, 2026cs.ITscore 0
- Equilibrium Propagation for Non-Conservative Systems
Antonino Emanuele Scurria, Dimitri Vanden Abeele, Bortolo Matteo Mognetti, Serge Massar
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- When Should Agents Coordinate in Differentiable Sequential Decision Problems?
Caleb Probine, Su Ann Low, David Fridovich-Keil, Ufuk Topcu
arXivSource: arxiv.orgFeb 3, 2026cs.MAscore 0
- Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging
Alexandru Meterez, Pranav Ajit Nair, Depen Morwani, Cengiz Pehlevan, Sham Kakade
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods
Grigory Begunov, Alexander Tyurin
arXivSource: arxiv.orgFeb 3, 2026cs.DCscore 0
- The Role of Target Update Frequencies in Q-Learning
Simon Weissmann, Tilman Aach, Benedikt Wille, Sebastian Kassing, Leif Döring
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- Representation Geometry as a Diagnostic for Out-of-Distribution Robustness
Ali Zia, Farid Hazratian
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- A categorical framework for cellular automata
A. Castillo-Ramirez, A. Vazquez-Aceves, A. Zaldivar-Corichi
arXivSource: arxiv.orgFeb 3, 2026cs.FLscore 0
- A Probabilistic Framework for Solving High-Frequency Helmholtz Equations via Diffusion Models
Yicheng Zou, Samuel Lanthaler, Hossein Salahshoor
arXivSource: arxiv.orgFeb 3, 2026cs.LGscore 0
- Causal-Informed Hybrid Online Adaptive Optimization for Ad Load Personalization in Large-Scale Social Networks
Aakash Mishra, Qi Xu, Zhigang Hua, Keyu Nie, Vishwanath Sangale, Vishal Vaingankar, Jizhe Zhang, Ren Mao
arXivSource: arxiv.orgFeb 3, 2026cs.SIscore 0
- Contextual Information Allocation in Shared-State Cognitive Models: An Information-Theoretic Bound
Song-Ju Kim
arXivSource: arxiv.orgFeb 3, 2026cs.AIscore 0
- On the Multi-Commodity Flow with convex objective function: Column-Generation approaches
Guillaume Beraud-Sudreau, Lucas Létocart, Youcef Magnouche, Sébastien Martin
arXivSource: arxiv.orgFeb 3, 2026cs.NIscore 0
- Implementation Challenges in Quantum Key Distribution
Abel C. H. Chen
arXivSource: arxiv.orgFeb 2, 2026cs.CRscore 0
- Local exponential stability of mean-field Langevin descent-ascent and associated particle system
Geuntaek Seo, Minseop Shin, Pierre Monmarché, Beomjun Choi
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- Two-chart Beltrami Optimization for Distortion-Controlled Spherical Bijection with Application to Brain Surface Registration
Zhehao Xu, Lok Ming Lui
arXivSource: arxiv.orgFeb 2, 2026cs.GRscore 0
- The Effect of Mini-Batch Noise on the Implicit Bias of Adam
Matias D. Cattaneo, Boris Shigida
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- Stein-Rule Shrinkage for Stochastic Gradient Estimation in High Dimensions
M. Arashi, M. Amintoosi
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- Sharp Thresholds for Temporal Motifs and Doubling Time in Random Temporal Graphs
Henry Austin, George B. Mertzios, Paul G. Spirakis
arXivSource: arxiv.orgFeb 2, 2026cs.DMscore 0
- Autocorrelated Optimize-via-Estimate: Predict-then-Optimize versus Finite-sample Optimal
Zichun Wang, Gar Goei Loke, Ruiting Zuo
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- Position: The Need for Ultrafast Training
Duc Hoang
arXivSource: arxiv.orgFeb 2, 2026cs.ARscore 0
- Efficient Swap Regret Minimization in Combinatorial Bandits
Andreas Kontogiannis, Vasilis Pollatos, Panayotis Mertikopoulos, Ioannis Panageas
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- The $\infty$-category of $\infty$-categories in simplicial type theory
Daniel Gratzer, Jonathan Weinberger, Ulrik Buchholtz
arXivSource: arxiv.orgFeb 2, 2026cs.LOscore 0
- Spectral Superposition: A Theory of Feature Geometry
Georgi Ivanov, Narmeen Oozeer, Shivam Raval, Tasana Pejovic, Shriyash Upadhyay, Amir Abdullah
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory
Yuanhe Zhang, Jason D. Lee, Fanghui Liu
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- Maximizing Reliability with Bayesian Optimization
Jack M. Buckingham, Ivo Couckuyt, Juergen Branke
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- Finite-Sample Wasserstein Error Bounds and Concentration Inequalities for Nonlinear Stochastic Approximation
Seo Taek Kong, R. Srikant
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- A two-player version of the assignment problem
Florian Galliot, Nacim Oijid, Jonas Sénizergues
arXivSource: arxiv.orgFeb 2, 2026cs.GTscore 0
- When pre-training hurts LoRA fine-tuning: a dynamical analysis via single-index models
Gibbs Nwemadji, Bruno Loureiro, Jean Barbier
arXivSource: arxiv.orgFeb 2, 2026cs.LGscore 0
- A Unified Matrix-Spectral Framework for Stability and Interpretability in Deep Learning
Ronald Katende
arXivSource: arxiv.orgFeb 1, 2026cs.LGscore 0
- Capabilities and Fundamental Limits of Latent Chain-of-Thought
Jiaxuan Zou, Yaozhong Xiong, Yong Liu
arXivSource: arxiv.orgFeb 1, 2026cs.AIscore 0
- SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
Jialong Sun, Zeming Wei, Jiaxuan Zou, Jiacheng Gong, Jie Fu, Chengyang Dong, Heng Xu, Jialong Li
arXivSource: arxiv.orgFeb 1, 2026cs.LGscore 0
- When Does Cheap Physics Help? Gated Multi-Fidelity Physics-Informed Networks with Provable Sample Savings and Conformal Guarantees
laf Yunus Laitinen Imanov, Rana Irem Turhan, Isgandar Jafarli
arXivSource: arxiv.orgFeb 1, 2026cs.LGscore 0
- L-Moment-Based LOS and NLOS Channel Characterization via Four-parameter Kappa Distribution for AoA BLE CTE Measurements
Hamed Talebian, Aamir Mahmood, Mikael Gidlund
arXivSource: arxiv.orgFeb 1, 2026cs.ITscore 0
- High-accuracy sampling for diffusion models and log-concave distributions
Fan Chen, Sinho Chewi, Constantinos Daskalakis, Alexander Rakhlin
arXivSource: arxiv.orgFeb 1, 2026cs.LGscore 0
- Methods for Counting and Enumerating Set Partitions
Arnav Khinvasara, Alexander Pikovski
arXivSource: arxiv.orgFeb 1, 2026cs.DSscore 0
- Phase Transitions for Feature Learning in Neural Networks
Andrea Montanari, Zihao Wang
arXivSource: arxiv.orgFeb 1, 2026cs.LGscore 0
- Rod Flow: A Continuous-Time Model for Gradient Descent at the Edge of Stability
Eric Regis, Sinho Chewi
arXivSource: arxiv.orgFeb 1, 2026cs.LGscore 0
- Effective Frontiers: A Unification of Neural Scaling Laws
Jiaxuan Zou, Zixuan Gong, Ye Su, Huayi Tang, Yong Liu
arXivSource: arxiv.orgFeb 1, 2026cs.LGscore 0
- Quality-Diversity Optimization as Multi-Objective Optimization
Xi Lin, Ping Guo, Yilu Liu, Qingfu Zhang, Jianyong Sun
arXivSource: arxiv.orgJan 31, 2026cs.LGscore 0
- Partition of Unity Neural Networks for Interpretable Classification with Explicit Class Regions
Akram Aldroubi
arXivSource: arxiv.orgJan 31, 2026cs.LGscore 0
- Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds
Sujoy Bhore, Liana Khazaliya, Fionn Mc Inerney
arXivSource: arxiv.orgJan 31, 2026cs.CCscore 0
- Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities
Marco Nurisso, Pierrick Leroy, Giovanni Petri, Francesco Vaccarino
arXivSource: arxiv.orgJan 31, 2026cs.LGscore 0
- The complexity of finding coset-generating polymorphisms and the promise metaproblem
Manuel Bodirsky, Armin Weiß
arXivSource: arxiv.orgJan 31, 2026cs.CCscore 0
- Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning
Shahryar Zehtabi, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher Brinton
arXivSource: arxiv.orgJan 31, 2026cs.LGscore 0