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

Learning Theory

5,312 papers

Papers per year

Papers

Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning? EACL 2023
Certifiable Out-of-Distribution Generalization AAAI 2023
On Model Selection Consistency of Lasso for High-Dimensional Ising Models AISTATS 2023
Optimality of Message-Passing Architectures for Sparse Graphs NIPS 2023
On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization ICML 2023
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks NIPS 2023
Strong Lottery Ticket Hypothesis with $\varepsilon$–perturbation AISTATS 2023
The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks CONLL 2023
Quantifying Train-Evaluation Overlap with Nearest Neighbors ACL 2023
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring COLT 2023
Smooth Non-stationary Bandits ICML 2023
How Fragile is Relation Extraction under Entity Replacements? EMNLP 2023
Beyond Strict Competition: Approximate Convergence of Multi-agent Q-Learning Dynamics IJCAI 2023
NEWTON: Are Large Language Models Capable of Physical Reasoning? EMNLP 2023
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies ICML 2023
The noise level in linear regression with dependent data NIPS 2023
Fundamental Tradeoffs in Learning with Prior Information ICML 2023
Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance NIPS 2023
A unified framework for information-theoretic generalization bounds NIPS 2023
The Power of Contrast for Feature Learning: A Theoretical Analysis JMLR 2023
Incentive-aware Contextual Pricing with Non-parametric Market Noise AISTATS 2023
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making ICML 2023
On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm ICML 2023
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent NIPS 2023
Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete NIPS 2023