conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4,950 papers

Papers per year

Papers

Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels ICML 2023
The Regret of Exploration and the Control of Bad Episodes in Reinforcement Learning ICML 2023
Settling the Reward Hypothesis ICML 2023
Online Mechanism Design for Information Acquisition ICML 2023
On the Connection Between MPNN and Graph Transformer ICML 2023
Extrapolated Random Tree for Regression ICML 2023
On the Robustness of Text Vectorizers ICML 2023
Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces ICML 2023
Lower Bounds for Learning in Revealing POMDPs ICML 2023
Tighter Bounds on the Expressivity of Transformer Encoders ICML 2023
Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations ICML 2023
What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective ICML 2023
A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations ICML 2023
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data ICML 2023
Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement ICML 2023
Generalization Bounds using Data-Dependent Fractal Dimensions ICML 2023
The Computational Complexity of Concise Hypersphere Classification ICML 2023
Why Target Networks Stabilise Temporal Difference Methods ICML 2023
Improved Algorithms for White-Box Adversarial Streams ICML 2023
Non-stationary Reinforcement Learning under General Function Approximation ICML 2023
A Theoretical Analysis of the Learning Dynamics under Class Imbalance ICML 2023
Towards Reliable Neural Specifications ICML 2023
Hidden Symmetries of ReLU Networks ICML 2023
Width and Depth Limits Commute in Residual Networks ICML 2023
Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes ICML 2023