Cover Image

Analyzing Cost-Sensitive Surrogate Losses via $\mathcal{H}$-calibration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shah, Sanket, Tambe, Milind, Finocchiaro, Jessie
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize
by: Shah, Sanket, et al.
Published: (2023)

Efficient Public Health Intervention Planning Using Decomposition-Based Decision-Focused Learning
by: Shah, Sanket, et al.
Published: (2024)

Evaluating the Effectiveness of Index-Based Treatment Allocation
by: Boehmer, Niclas, et al.
Published: (2024)

Trading off Consistency and Dimensionality of Convex Surrogates for the Mode
by: Nueve, Enrique, et al.
Published: (2024)

Finite-Horizon Single-Pull Restless Bandits: An Efficient Index Policy For Scarce Resource Allocation
by: Xiong, Guojun, et al.
Published: (2025)

Structured Prediction with Abstention via the Lovász Hinge
by: Finocchiaro, Jessie, et al.
Published: (2025)

Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous Agents
by: Gordon, Lucia, et al.
Published: (2024)

Three Types of Calibration with Properties and their Semantic and Formal Relationships
by: Derr, Rabanus, et al.
Published: (2025)

Lightweight Robust Direct Preference Optimization
by: Kim, Cheol Woo, et al.
Published: (2025)

Preference Robustness for DPO with Applications to Public Health
by: Kim, Cheol Woo, et al.
Published: (2025)

Reinforcement learning with combinatorial actions for coupled restless bandits
by: Xu, Lily, et al.
Published: (2025)

Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards
by: Verma, Shresth, et al.
Published: (2024)

Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits
by: Liang, Biyonka, et al.
Published: (2024)

On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow
by: Wang, Tonghan, et al.
Published: (2024)

Smoothed Elicitation Complexity for Approximate $Γ$-calibration of Discrete Classification Tasks
by: Finocchiaro, Jessica, et al.
Published: (2026)

Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
by: Kong, Lingkai, et al.
Published: (2025)

Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents
by: Tec, Mauricio, et al.
Published: (2025)

The Bandit Whisperer: Communication Learning for Restless Bandits
by: Zhao, Yunfan, et al.
Published: (2024)

Improving the Prediction of Individual Engagement in Recommendations Using Cognitive Models
by: Seow, Roderick, et al.
Published: (2024)

Decisions and Deployment: The Five-Year SAHELI Project (2020-2025) on Restless Multi-Armed Bandits for Improving Maternal and Child Health
by: Verma, Shresth, et al.
Published: (2026)

Contrasting local and global modeling with machine learning and satellite data: A case study estimating tree canopy height in African savannas
by: Rolf, Esther, et al.
Published: (2024)

Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits
by: Banerjee, Siddhartha, et al.
Published: (2022)

Dual-Mandate Patrols: Multi-Armed Bandits for Green Security
by: Xu, Lily, et al.
Published: (2020)

Bayesian Collaborative Bandits with Thompson Sampling for Improved Outreach in Maternal Health Program
by: Dasgupta, Arpan, et al.
Published: (2024)

Consistency Conditions for Differentiable Surrogate Losses
by: Khurana, Drona, et al.
Published: (2025)

Boosting Offline Optimizers with Surrogate Sensitivity
by: Dao, Manh Cuong, et al.
Published: (2025)

Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Losses
by: Cao, Yuzhou, et al.
Published: (2025)

IRL for Restless Multi-Armed Bandits with Applications in Maternal and Child Health
by: Jain, Gauri, et al.
Published: (2024)

Reward Shaping for Inference-Time Alignment: A Stackelberg Game Perspective
by: Wang, Haichuan, et al.
Published: (2026)

What is the Right Notion of Distance between Predict-then-Optimize Tasks?
by: Rodriguez-Diaz, Paula, et al.
Published: (2024)

Learning Differentiable Surrogate Losses for Structured Prediction
by: Yang, Junjie, et al.
Published: (2024)

Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization
by: Zhao, Yunfan, et al.
Published: (2023)

Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning
by: Kim, Cheol Woo, et al.
Published: (2025)

Non-Stationary Online Structured Prediction with Surrogate Losses
by: Sakaue, Shinsaku, et al.
Published: (2025)

A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
by: Behari, Nikhil, et al.
Published: (2024)

Fairness for Workers Who Pull the Arms: An Index Based Policy for Allocation of Restless Bandit Tasks
by: Biswas, Arpita, et al.
Published: (2023)

Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
by: Ai, Rui, et al.
Published: (2025)

Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation
by: Chen, Qiyuan, et al.
Published: (2022)

A Universal Growth Rate for Learning with Smooth Surrogate Losses
by: Mao, Anqi, et al.
Published: (2024)

Sensitivity Analysis On Loss Landscape
by: Faroz, Salman
Published: (2024)