← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4950 directly classified papers

Papers per year

Papers

Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective NIPS 2024
Incentivizing Quality Text Generation via Statistical Contracts NIPS 2024
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis NIPS 2024
HEMM: Holistic Evaluation of Multimodal Foundation Models NIPS 2024
Learning to Understand: Identifying Interactions via the Möbius Transform NIPS 2024
Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input NIPS 2024
Bridging OOD Detection and Generalization: A Graph-Theoretic View NIPS 2024
Replicable Uniformity Testing NIPS 2024
Cryptographic Hardness of Score Estimation NIPS 2024
ptwt - The PyTorch Wavelet Toolbox JMLR 2024
Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit JMLR 2024
A Rainbow in Deep Network Black Boxes JMLR 2024
Investigating Data Contamination in Modern Benchmarks for Large Language Models NAACL 2024
Evaluating Step-by-Step Reasoning through Symbolic Verification NAACL 2024
BotChat: Evaluating LLMs’ Capabilities of Having Multi-Turn Dialogues NAACL 2024
Differentially Private Topological Data Analysis JMLR 2024
Euler Characteristic Tools for Topological Data Analysis JMLR 2024
Identifying Causal Effects using Instrumental Time Series: Nuisance IV and Correcting for the Past JMLR 2024
Emergence of heavy tails in homogenized stochastic gradient descent NIPS 2024
Fundamental Convergence Analysis of Sharpness-Aware Minimization NIPS 2024
A generalized neural tangent kernel for surrogate gradient learning NIPS 2024
Lookback Prophet Inequalities NIPS 2024
Measuring Per-Unit Interpretability at Scale Without Humans NIPS 2024
On the Intrinsic Structures of Spiking Neural Networks JMLR 2024
On the Relationship Between Relevance and Conflict in Online Social Link Recommendations NIPS 2023