English
Related papers

Related papers: Doing More With Less: Mismatch-Based Risk-Limiting…

200 papers

AI coding scaffolds like Claude Code and Codex use retrying: blocking actions flagged as risky and continuing the trajectory. We study retrying from an AI control perspective, which treats the model as potentially adversarial. We find that…

Artificial Intelligence · Computer Science 2026-05-27 James Lucassen , Adam Kaufman

This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on the fact that…

Machine Learning · Computer Science 2020-11-10 Botao Hao , Yaqi Duan , Tor Lattimore , Csaba Szepesvári , Mengdi Wang

In safety-critical decision-making, the environment may evolve over time, and the learner adjusts its risk level accordingly. This work investigates risk-averse online optimization in dynamic environments with varying risk levels, employing…

Optimization and Control · Mathematics 2025-12-30 Siyi Wang , Zifan Wang , Karl H. Johansson

In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error…

Machine Learning · Computer Science 2025-07-09 Lukas Fluri , Leon Lang , Alessandro Abate , Patrick Forré , David Krueger , Joar Skalse

Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a…

Computation and Language · Computer Science 2026-02-13 Usman Naseem , Gautam Siddharth Kashyap , Rafiq Ali , Ebad Shabbir , Sushant Kumar Ray , Abdullah Mohammad , Agrima Seth

Robust estimators for linear regression require non-convex objective functions to shield against adverse affects of outliers. This non-convexity brings challenges, particularly when combined with penalization in high-dimensional settings.…

Computation · Statistics 2025-08-08 David Kepplinger , Siqi Wei

Randomized controlled trials (RCTs) are the gold standard for evaluating the causal effect of a treatment; however, they often have limited sample sizes and sometimes poor generalizability. On the other hand, non-randomized, observational…

Methodology · Statistics 2021-09-23 Shuxiao Chen , Bo Zhang , Ting Ye

Machine learning (ML) models often exhibit bias that can exacerbate inequities in biomedical applications. Fairness auditing, the process of evaluating a model's performance across subpopulations, is critical for identifying and mitigating…

Methodology · Statistics 2026-05-19 Jianhui Gao , Jessica Gronsbell

While randomized controlled trials (RCTs) are the gold standard for estimating treatment effects in medical research, there is increasing use of and interest in using real-world data for drug development. One such use case is the…

Methodology · Statistics 2021-10-11 Devin Incerti , Michael T Bretscher , Ray Lin , Chris Harbron

Cross-Context Review (CCR) improves LLM verification by separating production and review into independent sessions. A natural extension is multi-turn review: letting the reviewer ask follow-up questions, receive author responses, and review…

Computation and Language · Computer Science 2026-03-18 Song Tae-Eun

We tackle the problem of estimating risk measures of the infinite-horizon discounted cost within a Markov cost process. The risk measures we study include variance, Value-at-Risk (VaR), and Conditional Value-at-Risk (CVaR). First, we show…

Machine Learning · Computer Science 2024-04-12 Gugan Thoppe , L. A. Prashanth , Sanjay Bhat

High-quality data annotation is an essential but laborious and costly aspect of developing machine learning-based software. We explore the inherent tradeoff between annotation accuracy and cost by detecting and removing minority reports --…

Machine Learning · Computer Science 2025-04-15 Hsuan Wei Liao , Christopher Klugmann , Daniel Kondermann , Rafid Mahmood

Algorithmic risk assessment instruments (RAIs) increasingly inform decision-making in criminal justice. RAIs largely rely on arrest records as a proxy for underlying crime. Problematically, the extent to which arrests reflect overall…

Computers and Society · Computer Science 2023-05-15 Miri Zilka , Riccardo Fogliato , Jiri Hron , Bradley Butcher , Carolyn Ashurst , Adrian Weller

In this paper we study a family of variance reduction methods with randomized batch size---at each step, the algorithm first randomly chooses the batch size and then selects a batch of samples to conduct a variance-reduced stochastic…

Machine Learning · Computer Science 2018-08-08 Xuanqing Liu , Cho-Jui Hsieh

The entropic value-at-risk (EVaR) is a new coherent risk measure, which is an upper bound for both the value-at-risk (VaR) and conditional value-at-risk (CVaR). As important properties, the EVaR is strongly monotone over its domain and…

Portfolio Management · Quantitative Finance 2020-04-17 Amir Ahmadi-Javid , Malihe Fallah-Tafti

Multi-view spectral clustering, which aims at yielding an agreement or consensus data objects grouping across multi-views with their graph laplacian matrices, is a fundamental clustering problem. Among the existing methods, Low-Rank…

Machine Learning · Computer Science 2016-08-22 Yang Wang , Wenjie Zhang , Lin Wu , Xuemin Lin , Meng Fang , Shirui Pan

We study a risk-constrained version of the stochastic shortest path (SSP) problem, where the risk measure considered is Conditional Value-at-Risk (CVaR). We propose two algorithms that obtain a locally risk-optimal policy by employing four…

Machine Learning · Statistics 2018-10-23 Prashanth L. A.

Algorithmic lending has transformed the consumer credit landscape, with complex machine learning models now commonly used to make or assist underwriting decisions. To comply with fair lending laws, these algorithms typically exclude legally…

Applications · Statistics 2025-12-25 Madison Coots , Robert Bartlett , Julian Nyarko , Sharad Goel

We study multiwinner elections with approval-based preferences. An instance of a multiwinner election consists of a set of alternatives, a population of voters---each voter approves a subset of alternatives, and the desired committee size…

Computer Science and Game Theory · Computer Science 2019-10-15 Piotr Skowron

We develop several tools for the determination of sample size and design for Medicaid and healthcare audits. The goal of these audits is to examine a population of claims submitted by a healthcare provider for reimbursement by a third party…

Methodology · Statistics 2018-09-07 Michelle Norris
‹ Prev 1 8 9 10 Next ›