← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4950 directly classified papers

Papers per year

Papers

Autonomous Concept Drift Threshold Determination AAAI 2026
Parameter-free Optimal Rates for Nonlinear Semi-Norm Contractions with Applications to Q-Learning AAAI 2026
Provably Data-Driven Projection Method for Quadratic Programming AAAI 2026
Forest vs Tree: The (N, K) Trade-off in Reproducible ML Evaluation AAAI 2026
Fast Conformal Prediction Using Conditional Interquantile Intervals AAAI 2026
Aggregate-Combine-Readout GNNs Can Express Logical Classifiers Beyond the Logic C2 AAAI 2026
Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization AAAI 2026
A Theoretical Analysis of Detecting Large Model-Generated Time Series AAAI 2026
Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators AAAI 2026
Quantifying and Improving Adaptivity in Conformal Prediction Through Input Transformations AAAI 2026
An Information Theoretic Evaluation Metric for Strong Unlearning AAAI 2026
Revisiting Differentiable Structure Learning: Inconsistency of L1 Penalty and Beyond AAAI 2026
Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms AAAI 2026
Exploiting Space Folding by Neural Networks AAAI 2026
Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models AAAI 2026
Connectivity-Guided Sparsification of 2-FWL GNNs: Preserving Full Expressivity with Improved Efficiency AAAI 2026
Enhancing Kernel Power $K$-means: Scalable and Robust Clustering with Random Fourier Features and Possibilistic Method AAAI 2026
FlorE: Integrating Full Lorentz Group and Directional Offsets for Effective Knowledge Graph Embedding AAAI 2026
Learning from Answer Sets via Single-Shot Disjunctive ASP Encoding AAAI 2026
Active Learning of Symbolic Automata over Rational Numbers AAAI 2026
The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic AAAI 2026
Tractable Weighted First-Order Model Counting with Bounded Treewidth Binary Evidence AAAI 2026
Description Logics with Two Types of Definite Descriptions: Complexity, Expressiveness, and Automated Deduction AAAI 2026
Structural Approach to Guiding a Present-Biased Agent AAAI 2026
Promises Made, Promises Kept: Safe Pareto Improvements via Ex Post Verifiable Commitments AAAI 2026