Conditional-Value-At-Risk

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 25% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 39

All topics

Robust Risk-Sensitive Reinforcement Learning from Corrupted Human Feedback
Sep 30, 2026Xinyi Ni, Lifeng LaiReinforcement Learning From Human Feedback Conditional-Value-At-Risk
Department of Electrical and Computer Engineering, University of California, Davis, CA 95616, USA
Tail-Aware Geometry Learning for Conformal Ellipsoids
Sep 23, 2026Xiang ZhangOnline Conformal Prediction Uncertainty Quantification
School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore
CVaR anchor regression protects against rare shifts
Sep 22, 2026Malte LondschienCovariate Shift Conditional-Value-At-Risk
Linear Exponential Quadratic Gaussian Covariance Steering
Sep 14, 2026Chiran B. Cherian, Yasemin Isik, Abhishek HalderLinear Quadratic Regulator Covariance
Department of Aerospace Engineering, Iowa State University, Ames, IA 50011, USA · Department of Mathematics, Iowa State University, Ames, IA 50011, USA
Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations
Sep 11, 2026Tong Li, Saunak Kumar Panda, Yisha XiangConditional-Value-At-Risk Offline Reinforcement Learning
Department of Industrial and Systems Engineering, University of Houston, 4302 University Dr, Houston, 77004, TX, USA. · Department of Decision and Information Science, University of Houston, 4302 University Dr, Houston, 77004, TX, USA.
The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems
Aug 31, 2026Bardia Mohammadi, Laurent BindschaedlerRuntime Safety Filtering Agentic Deployments
Max Planck Institute for Software Systems Saarbrücken, Germany
BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Safe Reinforcement Learning
Aug 31, 2026Dongsheng Hou, Yanqiao Chen, Yuhan RuiConditional-Value-At-Risk Proximal Policy Optimization
Southern University of Science and Technology
Rules or Character? Scaling Laws for AI Safety Design
Aug 13, 2026Satoshi Takahashi, Nobuji Kouno, Masaaki Komatsu +1Artificial Intelligence Safety Fragility
AI Medical Engineering Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan · Division of Medical AI Research and Development, National Cancer Center Research Institute, Tokyo, Japan
Beyond Forecasting: Recasting Volatility Control as a Routing Problem
Aug 11, 2026Hongji Pu, Leyang ZhouVolatility Conditional-Value-At-Risk
University of Illinois, Urbana-Champaign Urbana, Illinois, USA
Adaptive Finite-Budget Training for CVaR Risk-Aware Q-Learning
Aug 5, 2026Yifan Wu, Junjie Lei, Wenjie HuangConditional-Value-At-Risk Q-Learning
Department of Data and Systems Engineering The University of Hong Kong Hong Kong, Hong Kong SAR
Online Policy Evaluation for MDPs with Dynamic UBSR Measures
Jul 25, 2026Weikai Wang, Erick DelageConditional-Value-At-Risk Markov Decision Processes
GERAD & Department of Decision Sciences, HEC Montr´eal, Canada
Deep Reinforcement Learning for Reliability Based Bi-Objective Portfolio Optimization
Jul 7, 2026Sounaq Das, Tanmay Sen, Raghu Nandan Sengupta +1Portfolio Optimization Conditional-Value-At-Risk
Indian Institute of Management Amritsar · Amritsar, India · SQC & OR Unit +7
Computing Monetary Risk Measures in Linear Time
Jul 6, 2026Palash Agrawal, Gersi Doko, Maeve Burwell +1Conditional-Value-At-Risk Risk
∗Equal contribution.
Value of Information under Imprecise Probabilities: Decision-Rule-Specific Values and Fixed-Measure Envelopes on a Credal Set
Jun 26, 2026Rowan IskandarConditional-Value-At-Risk Minimax
Medtronic Trading Sàrl, Tolochenaz, VD, Switzerland · Center for Evidence Synthesis in Health, Brown University School of Public Health, Providence, RI, USA
RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance
Jun 26, 2026Shiqiang GongDiffusion-Based Reinforcement Learning Methods Model-Based Reinforcement Learning
Northwestern Polytechnical University
Utility-Constrained Policy Optimization
Jun 12, 2026Mehrdad Moghimi, Bernardo Avila PiresSafety Constraints Markov Decision Processes
York University Toronto, Canada · Google DeepMind London, United Kingdom
Benchmarking Quantum Algorithmic Resilience for CVaR Portfolio Optimization: The Expressibility-Coherence Trade-off
Jun 5, 2026Prashik N. Somkuwar, K. Srinivasan, G. RaghavanQuantum Approximate Optimization Algorithm Variational Quantum Circuits
School of Quantum Technology, Defence Institute of Advanced Technology, Pune, India
Conformal Risk-Averse Decision Making with Action Conditional Guarantee
Jun 4, 2026Zihan Zhu, Shayan Kiyani, George Pappas +1Conformal Risk Control Online Conformal Prediction
University of Pennsylvania
ReSGA: A Large Tail Risk Model for Learning Value-at-Risk and Expected Shortfall
Jun 3, 2026Yichi Zhang, Ke Zhu, Zhoufan ZhuConditional-Value-At-Risk Long-Tailed Distribution
Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong · Wang Yanan Institute for Studies in Economics, Xiamen University, China · Department of Finance, School of Economics, Xiamen University, China
Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States
May 31, 2026Yujiao ChenConditional-Value-At-Risk Markov Decision Processes
Massachusetts Institute of Technology · Cambridge, MA 02139, USA
Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference
May 29, 2026Catherine Chen, Jingyan Shen, Zhun Deng +1Conditional-Value-At-Risk Conformal Risk Control
Institute for Computational and Mathematical Engineering, Stanford University · Department of Computer Science, New York University · Department of Computer Science, University of North Carolina at Chapel Hill +1
Forward-Looking Stress Testing Under Macro Scenarios: Stable SVaR Estimation Using a Hybrid GPR-HS Framework with SACS
May 26, 2026Ujjwala VadrevuConditional-Value-At-Risk Covariance
On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents
May 20, 2026Oliver Mortensen, Mohammad Sadegh TalebiConditional-Value-At-Risk Value Functions
Department of Computer Science, University of Copenhagen.
Conflict-Aware Active Perception and Control in 3D Gaussian Splatting Fields via Control Barrier Functions
May 19, 2026Amirhossein Mollaei Khass, Athanasios Cosse, Vivek Pandey +1Viewpoint-Dependent Active Perception Control Barrier Functions
Department of Mechanical Engineering and Mechanics, Lehigh University, Bethlehem, PA, 18015, USA
On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions
May 18, 2026Choudur LakshminarayanQuantile Regression Long-Tailed Distribution
School of Business, Stevens Institute of Technology
A Hybrid Gaussian Process Regression Framework for Stable Volatility-Covariance Estimation: Evidence from Global Equity Indices
May 17, 2026Ujjwala VadrevuVolatility Conditional-Value-At-Risk
Financially Guided Deep Portfolio Optimization
May 16, 2026Rahul Fernandes, Travis DesellPortfolio Optimization Portfolio Construction
Department of Software Engineering Rochester Institute of Technology Rochester, New York, USA
R2V Agent: Teaching SLMs When to Ask for Help
May 15, 2026Raghu Vamshi Hemadri, Humaira Firdowse Mohammed, Rishabh Maheshwary +5Large Language Model Routing Cp-Agent
New York University Tandon School of Engineering · University of California, San Diego · ServiceNow Research +3
The Privacy Price of Tail-Risk Learning: Effective Tail Sample Size in Differentially Private CVaR Optimization
May 15, 2026El Mustapha MansouriConditional-Value-At-Risk Long-Tailed Distribution
School of Engineering, Institute of Science Tokyo, Yokohama, Kanagawa 226-8501, Japan
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
May 13, 2026Qisong He, Xinmiao Huang, Jinwei Hu +4Safety Constraints Robot Navigation
University of Liverpool, Liverpool, UK. · Universit´e Grenoble Alpes, Grenoble, France.
Actor-Critic Algorithm for Dynamic Expectile and CVaR
May 8, 2026Yudong Luo, Erick DelageConditional-Value-At-Risk Soft Actor-Critic
1GERAD & Department of Decision Sciences, HEC Montr´eal, Canada · 2Mila - Quebec AI Institute, Canada
Learning Material-Aware Hamiltonian Risk Fields for Safe Navigation
May 7, 2026Aditya Sai Ellendula, Yi Wang, Chandrajit BajajSafe Navigation Conditional-Value-At-Risk
Department of Computer Science, University of Texas at Austin, Austin, TX 78712, USA · Oden Institute, University of Texas at Austin, Austin, TX 78712, USA
Agentic, Context-Aware Risk Intelligence in the Internet of Value
May 7, 2026Basel Magableh, OmniRisk ResearchConditional-Value-At-Risk Artificial Intelligence Risk
School of Computer Science, Technological University Dublin, Ireland · Rayachain Lab, Dublin, Ireland
Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Risk
Apr 20, 2026Feras Al Taha, Eilyan BitarDistributionally-Robust Optimization Conditional-Value-At-Risk
School of Electrical and Computer Engineering, Cornell University, Ithaca, NY 14853 USA
Risk-Constrained Belief-Space Optimization for Safe Control under Latent Uncertainty
Apr 4, 2026Clinton Enwerem, John S. Baras, Calin BeltaModel Predictive Path Integral Conditional-Value-At-Risk
Institute for Systems Research, University of Maryland, College Park, MD, USA
Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity
Feb 3, 2026Aneri Muni, Vincent Taboga, Esther Derman +2Conditional-Value-At-Risk Bellman Equation
Universit´e de Montr´eal, Quebec, Canada · Mila - Quebec AI Institute, Quebec, Canada · GERAD & Department of Decision Sciences, HEC Montr´eal, Quebec, Canada
Cantelli Constrained Policy Optimization
Jan 30, 2026Rohan Tangri, Jan-Peter CalliessConditional-Value-At-Risk Safety Constraints
Machine Learning Research Group, University of Oxford, Oxford, United Kingdom
ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining
May 26, 2025Melis Ilayda Bal, Volkan Cevher, Michael MuehlebachLarge Language Model Pretraining Pretraining
Max Planck Institute for Intelligent Systems, Tübingen, Germany
Online simultaneous inference for quantiles via smoothed stochastic gradient descent
May 19, 2025Likai Chen, Georg Keilbar, Wei Biao WuQuantile Regression Exponential Family
Department of Mathematics and Statistics · Washington University in St.Louis · St.Louis, MO, USA +6

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

Robust Risk-Sensitive Reinforcement Learning from Corrupted Human Feedback

Xinyi Ni, Lifeng Lai

Department of Electrical and Computer Engineering, University of California, Davis, CA 95616, USA

Reinforcement Learning From Human Feedback Conditional-Value-At-Risk Offline Reinforcement Learning Feedback

Open paper AskPDF arXiv

Reinforcement learning with human feedback (RLHF) learns from human comparisons, which can be corrupted or deliberately manipulated. This paper studies online risk-sensitive RLHF with static conditional value-at-risk (CVaR) under adversarial preference-label flips. We consider additive linear rewards and a fixed-reference protocol with one comparison per episode and at most

C

flipped labels over

K

episodes. We propose weighted streamed-preference CVaR RLHF (WSP-CVaR-RLHF), which combines uncertainty-weighted reward estimation with optimistic augmented-state CVaR planning. For known transitions and normalized rewards, we establish the regret bound

\widetilde{O}\left(\frac{d}κ\sqrt{\frac{K}α}+\frac{dC}{κα}\right)

up to lower-order terms, where

d

is the reward-feature dimension,

α

is the CVaR level, and

κ

characterizes the preference link. The bound separates the clean statistical cost from the penalty caused by corrupted feedback. We further extend the analysis to unknown tabular transitions, where the trajectory distribution entering the CVaR objective must be learned together with the reward. We address the resulting coupled uncertainty using rectangular transition confidence sets, joint optimistic planning, and a history-level CVaR simulation argument. Experiments under four adversarial attacks demonstrate that WSP-CVaR-RLHF consistently reduces cumulative regret relative to its unweighted robust counterpart while preserving confidence-set coverage.

Momentum

Related topics

Latest papers 39