paper-with-me

Papers

Replicability and stability in learning

2023-04-07 · Zachary Chase, Shay Moran, Amir Yehudayoff

Replicability is essential in science as it allows us to validate and verify research findings. Impagliazzo, Lei, Pitassi and Sorrell (`22) recently initiated the study of replicability in machine learning. A learning algorithm is replicable if it typically produces the same output when applied on two i.i.d. inputs using the same internal randomness. We study a variant of replicability that does not involve fixing the randomness. An algorithm satisfies this form of replicability if it typically produces the same output when applied on two i.i.d. inputs (without fixing the internal randomness). This variant is called global stability and was introduced by Bun, Livni and Moran ('20) in the context of differential privacy. Impagliazzo et al. showed how to boost any replicable algorithm so that it produces the same output with probability arbitrarily close to 1. In contrast, we demonstrate that for numerous learning tasks, global stability can only be accomplished weakly, where the same output is produced only with probability bounded away from 1. To overcome this limitation, we introduce the concept of list replicability, which is equivalent to global stability. Moreover, we prove that list replicability can be boosted so that it is achieved with probability arbitrarily close to 1. We also describe basic relations between standard learning-theoretic complexity measures and list replicable numbers. Our results, in addition, imply that besides trivial cases, replicable algorithms (in the sense of Impagliazzo et al.) must be randomized. The proof of the impossibility result is based on a topological fixed-point theorem. For every algorithm, we are able to locate a "hard input distribution" by applying the Poincar\'{e}-Miranda theorem in a related topological setting. The equivalence between global stability and list replicability is algorithmic.

📄 PDF Abstract BibTeX arXiv:2304.03757

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

List Replicable Reinforcement Learning

2025-11-29 · Bohan Zhang, Michael Chen, A. Pavan, N. V. Vinodchandran 외 arxiv

Replicability is a fundamental challenge in reinforcement learning (RL), as RL algorithms are empirically observed to be unstable and sensitive to variations in training conditions. To formally address this issue, we stu…

Reinforcement Learning

Approximate Replicability in Learning

2025-10-23 · Max Hopkins, Russell Impagliazzo, Christopher Ye arxiv

Replicability, introduced by (Impagliazzo et al. STOC '22), is the notion that algorithms should remain stable under a resampling of their inputs (given access to shared randomness). While a strong and interesting notion…

Borsuk-Ulam and Replicable Learning of Large-Margin Halfspaces

2025-03-19 · Ari Blondal, Hamed Hatami, Pooya Hatami, Chavdar Lalov 외

Recent remarkable advances in learning theory have established that, for total concept classes, list replicability, global stability, differentially private (DP) learnability, and shared-randomness replicability all coin…

Learning Theory

Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization

2023-03-22 · Mark Bun, Marco Gaboardi, Max Hopkins, Russell Impagliazzo 외

The notion of replicable algorithms was introduced in Impagliazzo et al. [STOC '22] to describe randomized algorithms that are stable under the resampling of their inputs. More precisely, a replicable algorithm gives the…

PAC learning

Deconfounding and Causal Regularization for Stability and External Validity

2020-08-14 · Peter Bühlmann, Domagoj Ćevid

We review some recent work on removing hidden confounding and causal regularization from a unified viewpoint. We describe how simple and user-friendly techniques improve stability, replicability and distributional robust…