ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Nathan Kallus

Nathan Kallus

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

21

papers

401

total citations

papers (21)

Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning

NEURIPS 2020arXiv

Post-Contextual-Bandit Inference

NEURIPS 2021arXiv

Provable Offline Preference-Based Reinforcement Learning

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

NEURIPS 2022arXiv

What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment

NEURIPS 2022arXiv

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning

NEURIPS 2023arXiv

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

NEURIPS 2023arXiv

Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning

NEURIPS 2021arXiv

More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning

Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies

NEURIPS 2020arXiv

Control Variates for Slate Off-Policy Evaluation

NEURIPS 2021arXiv

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training

NEURIPS 2025arXiv

Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments

Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams

Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage

NEURIPS 2023arXiv

Value-Guided Search for Efficient Chain-of-Thought Reasoning

NEURIPS 2025arXiv

Estimating Structural Disparities for Face Models

The Implicit Delta Method

NEURIPS 2022arXiv

GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

NEURIPS 2025arXiv

Efficient Adaptive Experimentation with Noncompliance

NEURIPS 2025arXiv

Switching the Loss Reduces the Cost in Batch Reinforcement Learning