Key papers

• An exact information theory of generalization phase transitions in Bayesian diffusion models (2026)
  Henry Hunt et al.
  5.01
• Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay (2026)
  Xiaolong Li et al.
  5.01
• Local Synaptic Rules Can Implement a SIGReg Gradient Without Backpropagation (2026)
  Martin Andrews
  5.01
• A Defense of the Quadratic Model (2026)
  Alexandru Meterez et al.
  5.01
• Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning (2026)
  Scott M. Norton
  5.01
• Chaos Is a LADDER: Domain Generalization Beyond Invariance via Reweighting (2026)
  Yuhang Jiang et al.
  5.01
• The Multiscale Single-Index Model: A Stylized Model for Hierarchical Feature Learning (2026)
  Joan Bruna
  4.39
• Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization (2026)
  Ethan Smith
  4.39
• Learning from Noise: Effective-Rank Collapse and Out-of-Distribution Rejection in Restricted Boltzmann Machines (2026)
  Oshada Rathnayake et al.
  4.39
• Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs (2026)
  Shrestha Datta et al.
  4.39
• Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO) (2026)
  Haricharan Balasundaram et al.
  4.39
• Efficient Online Proportional Sampling with Applications to Smoothed Online Learning (2026)
  Amirmahdi Mirfakhar et al.
  4.39
• Scalable Optimal Transport Algorithm for Network Alignment (2026)
  Elaheh Hassani et al.
  4.39
• Gradient-Free Topology Adaptation for Power Flow Surrogates via In-Context Whitening (2026)
  Ayushi Jolotia et al.
  4.39
• Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training (2026)
  Anxhelo Shehu et al.
  4.39
• Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization (2026)
  Zhen Huang et al.
  4.39
• Functional Equivalence and Geometric Diversity in Neural Network Approximations: An Empirical Characterization (2026)
  Anuragine S A et al.
  4.39
• Variational meta-learning inference for low dimensional neural system identification (2026)
  Matteo Rufolo et al.
  4.39
• Riemannian Deep Learning: Modules, Networks, and Geometries (2026)
  Chen Ziheng
  4.39
• An Isotropy-Preserving Spectral Cap for Muon: Theory and Three Case Studies (2026)
  Jiachun Li
  4.39
• From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning (2026)
  Jiaxin Deng et al.
  4.39
• Hyperball May Not Be a Free Lunch (2026)
  Yihao Xiao et al.
  4.39
• \k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating (2026)
  Jianghui Wang et al.
  4.39
• Hidden Boundary Motion in Transformer Optimization: Function-Space Orthogonalization of Affine Weight and Bias Updates (2026)
  Zhang Gongyue et al.
  4.39
• Mini-batch Noise Lowers Sharpness via Dominant-Subspace Fluctuations (2026)
  Junho So et al.
  4.39
• Neural Network-Driven Volatility Drag Mitigation under Aggressive Leverage (2026)
  Christian Bongiorno et al.
  4.39
• SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation (2026)
  Aditya Dewan et al.
  4.39
• Distributed Convolutional Rank Regression over Decentralized Networks (2026)
  Chunjing Li et al.
  4.39
• DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton (2026)
  Nour Jamoussi et al.
  4.39
• The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning (2026)
  Peng Xie
  4.39
• Soft-Constrained Optimization of Latent Space in Variational Autoencoders (2026)
  Ye Shi
  4.39
• Greedy dynamical meta-learning (2026)
  Aria Yom
  4.39
• DECAF: De-Clustering for Adaptive Representational Unlearning (2026)
  Anjie Le et al.
  4.39
• Understanding Machine Unlearning Through the Lens of Mode Connectivity (2026)
  Jiali Cheng et al.
  4.39
• BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage (2026)
  Akarsh K. Nair et al.
  4.39
• Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension (2026)
  Jinhao Zhang et al.
  4.39
• Retraction-Free Optimization over the Stiefel Manifold for the LoRA Fine-Tuning (2026)
  Yuan Zhang et al.
  4.39
• Automated Numerical Stability Analysis of Deep Learning Operators (2026)
  Xinye Chen
  4.39
• Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm (2026)
  Wenzhi Zhong et al.
  4.39
• Between Gradient and Natural Gradient: A Continuum of LoRA Initializations (2026)
  Dianze Liu et al.
  4.39
• WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training (2026)
  Jianhao Ma et al.
  3.51
• Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets (2026)
  Javier Maass et al.
  3.51
• When Is Heterogeneous Distance-Decay Facility Location Tractable? A Structural Classification, Exact Methods, and a Real-World Study (2026)
  Zhou He et al.
  3.51
• 1-Lipschitz Neural Networks on Hadamard Manifolds (2026)
  Davide Murari et al.
  3.51
• Learning from the Descent Direction: Adaptive Gradient Descent under One-Sided H\"older Regularity (2026)
  Arzu Ahmadova et al.
  3.51
• Scale Weight Decay and Train Better (2026)
  Anuj Apte
  3.51
• Representation Costs in Data Science: Foundations and the Quasi-Banach Spaces of Deep Neural Networks (2026)
  Greg Ongie et al.
  3.45
• On the Convergence Analysis of Muon (2025)
  Wei Shen et al.
  2.91
• Coefficient-to-Basis Network: A Fine-Tunable Operator Learning Framework for Inverse Problems with Adaptive Discretizations and Theoretical Guarantees (2025)
  Zecheng Zhang et al.
  2.71
• Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation (2025)
  Jean Barbier et al.
  2.60
• Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling (2025)
  Alexandru Meterez et al.
  2.56
• Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One (2026)
  Qi Zhou et al.
  2.00
• First-order Constrained Trilevel Optimization Over Distributed Networks for Robust Coreset Selection (2026)
  Yang Jiao (Richard) et al.
  2.00
• Towards joint scaling laws with optimal batch size schedules (2026)
  Jiaxiang Li et al.
  2.00
• Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers (2026)
  Vincent Ryusuke Takahashi et al.
  2.00
• Multi-ResNets for Subspace Preconditioning in Constrained Optimization (2026)
  Merve Karakas and Christopher J. Williams and Emmanuel O. Balogun and Sadegh Sadeghi Tabas and Christian Brown and Nikhil Rao
  1.94
• Explaining Data Mixing Scaling Laws (2026)
  Rui Dai et al.
  1.94
• Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation (2026)
  Guo Yu et al.
  1.94
• NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning (2026)
  Tianlin Pan et al.
  1.94
• Demystifying Manifold Constraints in LLM Pre-training (2026)
  Kang An et al.
  1.89