conftrace_

heavy-tailed distribution

98 papers

Explore in graph

Co-occurring keywords

stochastic gradient descent (1091) robust estimation (168) robust statistics (102) stochastic optimization (1060) regret bound (1926) multi-armed bandit (1098) linear regression (282) mean estimation (70) stochastic differential equation (181) sample complexity (1169)

Papers

Outlier Robust and Sparse Estimation of Linear Regression Coefficients JMLR 2025
Linear Hypothesis Testing in High-Dimensional Expected Shortfall Regression with Heavy-Tailed Errors JMLR 2025
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling NAACL 2025
Cauchy Diffusion: A Heavy-tailed Denoising Diffusion Probabilistic Model for Speech Synthesis AAAI 2025
Emergence of heavy tails in homogenized stochastic gradient descent NIPS 2024
Linear Regression using Heterogeneous Data Batches NIPS 2024
(ε, u)-Adaptive Regret Minimization in Heavy-Tailed Bandits COLT 2024
Robust variance-regularized risk minimization with concomitant scaling AISTATS 2024
Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD NIPS 2024
Beyond Catoni: Sharper Rates for Heavy-Tailed and Robust Mean Estimation COLT 2024
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification NIPS 2024
Data-Driven Confidence Intervals with Optimal Rates for the Mean of Heavy-Tailed Distributions AISTATS 2024
Robust group and simultaneous inferences for high-dimensional single index model NIPS 2024
On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control JMLR 2024
Adaptive importance sampling for heavy-tailed distributions via $α$-divergence minimization AISTATS 2024
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models NIPS 2024
Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality COLT 2023
Piecewise Stationary Bandits under Risk Criteria AISTATS 2023
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions ICML 2023
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards ICML 2023
Optimality in Mean Estimation: Beyond Worst-Case, Beyond Sub-Gaussian, and Beyond $1+\alpha$ Moments NIPS 2023
Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction ICML 2023
Beyond Uniform Lipschitz Condition in Differentially Private Optimization ICML 2023
Robust Methods for High-Dimensional Linear Learning JMLR 2023
Robust High-Dimensional Low-Rank Matrix Estimation: Optimal Rate and Data-Adaptive Tuning JMLR 2023