Search Results for author:
Found 9 papers, 1 papers with code
Is Elo Rating Reliable? A Study Under Model Misspecification
Elo rating, widely used for skill assessment across diverse domains ranging from competitive games to large language models, is often understood as an incremental update algorithm for estimating a stationary Bradley-Terry (BT) model.
Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
On the miniF2F benchmark, it achieves a 57. 6% success rate (Pass@32), exceeding the previous best open-source model by 7. 6%.
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
This issue is amplified when using original problems for in-context learning.
Benign Overfitting in Out-of-Distribution Generalization of Linear Models
Benign overfitting refers to the phenomenon where an over-parameterized model fits the training data perfectly, including noise in the data, but still generalizes well to the unseen test data.
Factor Adjusted Spectral Clustering for Mixture Models
This paper studies a factor modeling-based approach for clustering high-dimensional data generated from a mixture of strongly correlated variables.
Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
This paper addresses this fundamental question by proving that, surprisingly, classical Maximum Likelihood Estimation (MLE) purely using source data (without any modification) achieves the minimax optimality for covariate shift under the well-specified setting.
On the Provable Advantage of Unsupervised Pretraining
Unsupervised pretraining, which learns a useful representation using a large amount of unlabeled data to facilitate the learning of downstream tasks, is a critical component of modern large-scale machine learning systems.
Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond
We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks, where the protocols might differ between one another, yet a procedure of obtaining local gradients is implicitly shared.
Second-order Information in First-order Optimization Methods
To the best of our knowledge, this is the first paper that seriously considers the necessity of square root among all adaptive methods.
