48 citations · 102 across the 15 of their papers we have counts for
15 papers
Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics
Moritz Firsching, Paul Lezeau, Salvatore Mercuri +8
As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this,…
ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities
Ezra Karger, Houtan Bastani, Chen Yueh-Han +4
Forecasts of future events are essential inputs into informed decision-making. Machine learning (ML) systems have the potential to deliver forecasts at scale, but there is no frame…
Approaching Human-Level Forecasting with Language Models
Danny Halawi, Fred Zhang, Chen Yueh-Han +1
Forecasting future events is important for policy and decision making. In this work, we study whether language models (LMs) can forecast at the level of competitive human forecaste…
Adaptive Regret for Bandits Made Possible: Two Queries Suffice
Zhou Lu, Qiuyi Zhang, Xinyi Chen +3
Fast changing states or volatile environments pose a significant challenge to online optimization, which needs to perform rapid adaptation under limited observation. In this paper,…
Constant Approximation for Individual Preference Stable Clustering
Anders Aamand, Justin Y. Chen, Allen Liu +4
Individual preference (IP) stability, introduced by Ahmadi et al. (ICML 2022), is a natural clustering objective inspired by stability and fairness constraints. A clustering is …
Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
Fred Zhang, Neel Nanda
Mechanistic interpretability seeks to understand the internal mechanisms of machine learning models, where localization -- identifying the important model components -- is a key st…
Robust Algorithms on Adaptive Inputs from Bounded Adversaries
Yeshwanth Cherapanamjeri, Sandeep Silwal, David P. Woodruff +3
We study dynamic algorithms robust to adaptive input generated from sources with bounded capabilities, such as sparsity or limited interaction. For example, we consider robust line…
Streaming Algorithms for Learning with Experts: Deterministic Versus Robust
David P. Woodruff, Fred Zhang, Samson Zhou
In the online learning with experts problem, an algorithm must make a prediction about an outcome on each of days (or times), given a set of experts who make predictions on…
Optimal Query Complexities for Dynamic Trace Estimation
David P. Woodruff, Fred Zhang, Qiuyi Zhang
We consider the problem of minimizing the number of matrix-vector queries needed for accurate trace estimation in the dynamic setting where our underlying matrix is changing slowly…
Online Prediction in Sub-linear Space
Binghui Peng, Fred Zhang
We provide the first sub-linear space and sub-linear regret algorithm for online learning with expert advice (against an oblivious adversary), addressing an open question raised re…
Faster Fundamental Graph Algorithms via Learned Predictions
Justin Y. Chen, Sandeep Silwal, Ali Vakilian +1
We consider the question of speeding up classic graph algorithms with machine-learned predictions. In this model, algorithms are furnished with extra advice learned from past or si…
Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms
Alexander Wei, Fred Zhang
We study the problem of improving the performance of online algorithms by incorporating machine-learned predictions. The goal is to design algorithms that are both consistent and r…
Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization
Samuel B. Hopkins, Jerry Li, Fred Zhang
We study the problem of estimating the mean of a distribution in high dimensions when either the samples are adversarially corrupted or the distribution is heavy-tailed. Recent dev…
A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates
Zhixian Lei, Kyle Luh, Prayaag Venkat +1
We study the algorithmic problem of estimating the mean of heavy-tailed random vector in , given i.i.d. samples. The goal is to design an efficient estimator that…
SGD on Neural Networks Learns Functions of Increasing Complexity
Preetum Nakkiran, Gal Kaplun, Dimitris Kalimeris +4
We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show…