English
Related papers

Related papers: Tail-behavior roadmap for sharp restart

200 papers

Exponential tail bounds for sums play an important role in statistics, but the example of the $t$-statistic shows that the exponential tail decay may be lost when population parameters need to be estimated from the data. However, it turns…

Statistics Theory · Mathematics 2022-03-22 Guenther Walther

We revisit the classic regret-minimization problem in the stochastic multi-armed bandit setting when the arm-distributions are allowed to be heavy-tailed. Regret minimization has been well studied in simpler settings of either bounded…

Machine Learning · Computer Science 2021-02-09 Shubhada Agrawal , Sandeep Juneja , Wouter M. Koolen

In this paper, we consider how to provide fast estimates of flow-level tail latency performance for very large scale data center networks. Network tail latency is often a crucial metric for cloud application performance that can be affected…

Networking and Internet Architecture · Computer Science 2022-10-03 Kevin Zhao , Prateesh Goyal , Mohammad Alizadeh , Thomas E. Anderson

Digital transformation forces companies to rethink their processes to meet current customer needs. Business Process Management (BPM) can provide the means to structure and tackle this change. However, most approaches to BPM face…

Software Engineering · Computer Science 2020-12-02 Marcus Fischer , Adrian Hofmann , Florian Imgrund , Christian Janiesch , Axel Winkelmann

Continuous-time reinforcement learning tasks commonly use discrete steps of fixed cycle times for actions. As practitioners need to choose the action-cycle time for a given task, a significant concern is whether the hyper-parameters of the…

Machine Learning · Computer Science 2023-06-02 Homayoon Farrahi , A. Rupam Mahmood

We study the tradeoff between fundamental risk and time. A time-constrained agent has to solve a problem. She dynamically allocates effort between implementing a risky initial idea and exploring alternatives. Discovering an alternative…

Theoretical Economics · Economics 2023-02-21 Christoph Carnehl , Johannes Schneider

We propose a mean functional which exists for any probability distributions, and which characterizes the Pareto distribution within the set of distributions with finite left endpoint. This is in sharp contrast to the mean excess plot which…

Methodology · Statistics 2024-04-05 Bernhard Klar

We investigate the application of the Adaptive Multilevel Splitting algorithm for the estimation of tail probabilities of solutions of Stochastic Differential Equations evaluated at a given time, and of associated temporal averages. We…

Probability · Mathematics 2019-03-27 Charles-Edouard Bréhier , Tony Lelièvre

Heavy-tailed metrics are common and often critical to product evaluation in the online world. While we may have samples large enough for Central Limit Theorem to kick in, experimentation is challenging due to the wide confidence interval of…

Applications · Statistics 2019-05-23 Jason , Wang , Pauline Burke

The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models. However, the impact of fine-tuning strategies on long-tail learning performance remains unexplored. In…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Jiang-Xin Shi , Tong Wei , Yu-Feng Li

With the widespread adoption of deep learning in visual tasks, Class-Incremental Learning (CIL) has become an important paradigm for handling dynamically evolving data distributions. However, CIL faces the core challenge of catastrophic…

Machine Learning · Computer Science 2026-03-04 Jinge Ma , Fengqing Zhu

In this paper we demonstrate a simple heuristic adaptive restart technique that can dramatically improve the convergence rate of accelerated gradient schemes. The analysis of the technique relies on the observation that these schemes…

Optimization and Control · Mathematics 2012-04-19 Brendan O'Donoghue , Emmanuel Candes

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the…

Machine Learning · Computer Science 2023-04-03 Matthias De Lange , Gido van de Ven , Tinne Tuytelaars

Redundancy for straggler mitigation, originally in data download and more recently in distributed computing context, has been shown to be effective both in theory and practice. Analysis of systems with redundancy has drawn significant…

Performance · Computer Science 2017-10-03 Mehmet Fatih Aktas , Pei Peng , Emina Soljanin

A particular direction of recent advance about stochastic deep-learning algorithms has been about uncovering a rather mysterious heavy-tailed nature of the stationary distribution of these algorithms, even when the data distribution is not…

Machine Learning · Computer Science 2022-04-28 Sayar Karmakar , Anirbit Mukherjee

Estimation of tail quantities, such as expected shortfall or Value at Risk, is a difficult problem. We show how the theory of nonlinear expectations, in particular the Data-robust expectation introduced in [5], can assist in the…

Statistics Theory · Mathematics 2018-02-15 Samuel N. Cohen

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the…

Artificial Intelligence · Computer Science 2026-05-08 Yuan Sui , Yulin Chen , Yibo Li , Xue Jiang , Yufei He , Yihong Dong , Xiaoxin He , Tianyu Gao , Bryan Hooi

In this article, we quantify the functional convergence of the rescaled random walk with heavy tails to a stable process.This generalizes the Generalized Central Limit Theorem for stable random variables infinite dimension. We show that…

Probability · Mathematics 2026-04-02 Lorick Huang , Laurent Decreusefond , Laure Coutin

Response latency -- the time taken to initiate or complete an action or task -- is one of the principal measures used to investigate the mechanisms subserving human and animal cognitive processes. The right tails of response latency…

Neurons and Cognition · Quantitative Biology 2009-08-25 Fermín Moscoso del Prado Martín

We introduce a new class of first passage time optimization driven by threshold resetting, inspired by many natural processes where crossing a critical limit triggers failure, degradation or transition. In here, search agents are…

Statistical Mechanics · Physics 2026-01-22 Arup Biswas , Satya N Majumdar , Arnab Pal