← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4950 directly classified papers

Papers per year

Papers

Score-based generative models are provably robust: an uncertainty quantification perspective NIPS 2024
Critical Gap Between Generalization Error and Empirical Error in Active Learning WACV 2024
Categorical Flow Matching on Statistical Manifolds NIPS 2024
Transformers Represent Belief State Geometry in their Residual Stream NIPS 2024
GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond NAACL 2024
Reproduction & Benchmarking of German Text Simplification Systems COLING 2024
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents NIPS 2024
Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought NIPS 2024
On the Scaling Laws of Geographical Representation in Language Models COLING 2024
When Is Inductive Inference Possible? NIPS 2024
The Space Complexity of Approximating Logistic Loss NIPS 2024
A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise NIPS 2024
On the Expressive Power of Tree-Structured Probabilistic Circuits NIPS 2024
Building a stable classifier with the inflated argmax NIPS 2024
Symmetry-Informed Governing Equation Discovery NIPS 2024
Principles for AI-Assisted Social Influence and Their Application to Social Mediation EMNLP 2024
Optimal Multiclass U-Calibration Error and Beyond NIPS 2024
A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers NIPS 2024
High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise JMLR 2024
Sharp analysis of power iteration for tensor PCA JMLR 2024
Deep linear networks for regression are implicitly regularized towards flat minima NIPS 2024
Grokking phase transitions in learning local rules with gradient descent JMLR 2024
Robust group and simultaneous inferences for high-dimensional single index model NIPS 2024
On the Connection between Lp- and Risk Consistency and its Implications on Regularized Kernel Methods JMLR 2024
Learning with a linear loss function: excess risk and estimation bounds for ERM, minmax MOM and their regularized versions with applications to robustness in sparse PCA. JMLR 2024