Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Simultaneous Swap Regret Minimization via KL-Calibration
Authors: Haipeng Luo, Spandan Senapati, Vatsal Sharan
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this work, we significantly generalize their result in the following ways: (a) in addition to smooth univariate forms, our algorithm also simultaneously achieves O(T 1/3) swap regret for any proper loss with a twice continuously differentiable univariate form (such as Tsallis entropy); (b) our bounds hold not only for pseudo swap regret that measures losses using the forecaster s distributions on predictions, but also hold for the actual swap regret that measures losses using the forecaster s actual realized predictions. We achieve so by introducing a new stronger notion of calibration called (pseudo) KL-Calibration, which we show is equivalent to the (pseudo) swap regret with respect to log loss. We prove that there exists an algorithm that achieves O(T 1/3) KL-Calibration error and provide an explicit algorithm that achieves O(T 1/3) pseudo KL-Calibration error. Moreover, we show that the same algorithm achieves O(T 1/3(log T) 1 3 log(T/δ)) swap regret with probability at least 1 δ for any proper loss with a smooth univariate form, which implies O(T 1/3) ℓ2-Calibration error. A technical contribution of our work is a new randomized rounding procedure and a non-uniform discretization scheme to minimize the swap regret for log loss. |
| Researcher Affiliation | Academia | Haipeng Luo USC EMAIL Spandan Senapati USC EMAIL Vatsal Sharan USC EMAIL |
| Pseudocode | Yes | We summarize the discussion so far in Algorithm 1. Algorithm 1 BM for log loss... Algorithm 2 The i-th external regret algorithm (Ai)... Algorithm 3 Exponentially Weighted Online Optimization (EWOOi) with scaled losses... Algorithm 4 Randomized rounding for log loss (RROUNDlog) |
| Open Source Code | No | The paper is a theory work and does not include experiments requiring code. |
| Open Datasets | No | The paper is a theory work and does not include experiments. |
| Dataset Splits | No | No datasets are mentioned or used for experiments in the paper. |
| Hardware Specification | No | The paper is a theory work and does not include experiments. |
| Software Dependencies | No | No specific software dependencies with version numbers are mentioned for experimental reproducibility, as the paper is theoretical. |
| Experiment Setup | No | The paper is a theory work and does not include experiments. |