Learning Theory

High-probability Convergence Bounds for Online Nonlinear Stochastic Gradient Descent under Heavy-tailed Noise AISTATS 2025 How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective ICML 2025 How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning ICLR 2025 How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction ICML 2025 How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning? AAAI 2025 How Do Large Language Monkeys Get Their Power (Laws)? ICML 2025 How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison EMNLP 2025 How Gradient descent balances features: A dynamical analysis for two-layer neural networks ICLR 2025 How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark EMNLP 2025 How Likely Do LLMs with CoT Mimic Human Reasoning? COLING 2025 How many samples are needed to train a deep neural network? ICLR 2025 How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning ICLR 2025 How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs ACL 2025 How rotation invariant algorithms are fooled by noise on sparse targets ALT 2025 How to Evaluate Reward Models for RLHF ICLR 2025 How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias ICML 2025 Humanity’s Last Code Exam: Can Advanced LLMs Conquer Human’s Hardest Code Competition? EMNLP 2025 Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning ICML 2025 ICL CIPHERS: Quantifying ”Learning” in In-Context Learning via Substitution Ciphers EMNLP 2025 Identifiable Object Representations under Spatial Ambiguities ICML 2025 Identifying and Mitigating Spurious Correlation in Multi-Task Learning CVPR 2025 Identifying Metric Structures of Deep Latent Variable Models ICML 2025 Identifying Noise in Human-Created Datasets using Training Dynamics from Generative Models EMNLP 2025 Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework EMNLP 2025 Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression ICLR 2025