English
Related papers

Related papers: PAWL-Forced Simulated Tempering

200 papers

In this work, the Parareal algorithm is applied to evolution problems that admit good low-rank approximations and for which the dynamical low-rank approximation (DLRA) can be used as time stepper. Many discrete integrators for DLRA have…

Numerical Analysis · Mathematics 2022-09-14 Benjamin Carrel , Martin J. Gander , Bart Vandereycken

Self-paced learning (SPL) mimics the cognitive process of humans, who generally learn from easy samples to hard ones. One key issue in SPL is the training process required for each instance weight depends on the other samples and thus…

Machine Learning · Computer Science 2018-07-09 Xuchao Zhang , Liang Zhao , Zhiqian Chen , Chang-Tien Lu

Prompt tuning prepends a soft prompt to the input embeddings or hidden states and only optimizes the prompt to adapt pretrained models (PTMs) to downstream tasks. The previous work manually selects prompt layers which are far from optimal…

Computation and Language · Computer Science 2023-11-01 Wei Zhu , Ming Tan

Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents. In order to contribute towards intuitive…

Systems and Control · Electrical Eng. & Systems 2020-03-03 Florian Köpf , Alexander Nitsch , Michael Flad , Sören Hohmann

We design and analyse variations of the classical Thompson sampling (TS) procedure for Bayesian optimisation (BO) in settings where function evaluations are expensive, but can be performed in parallel. Our theoretical analysis shows that a…

Machine Learning · Statistics 2017-05-26 Kirthevasan Kandasamy , Akshay Krishnamurthy , Jeff Schneider , Barnabas Poczos

The advent of contextual word embeddings -- representations of words which incorporate semantic and syntactic information from their context -- has led to tremendous improvements on a wide variety of NLP tasks. However, recent contextual…

Computation and Language · Computer Science 2021-06-09 Prakhar Gupta , Martin Jaggi

We consider the problem of selecting covariates in spatial linear models with Gaussian process errors. Penalized maximum likelihood estimation (PMLE) that enables simultaneous variable selection and parameter estimation is developed and,…

Methodology · Statistics 2012-02-24 Tingjin Chu , Jun Zhu , Haonan Wang

In tabular multi-agent reinforcement learning with average-cost criterion, a team of agents sequentially interacts with the environment and observes local incentives. We focus on the case that the global reward is a sum of local rewards,…

Optimization and Control · Mathematics 2021-10-26 Alec Koppel , Amrit Singh Bedi , Bhargav Ganguly , Vaneet Aggarwal

Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), optimize the…

Machine Learning · Computer Science 2026-05-21 Adam Ousherovitch , Ambuj Tewari

This work proposes an adaptive sequential Monte Carlo sampling algorithm to solve Bayesian inverse problems in scenarios where likelihood evaluations are costly but can be approximated using a surrogate model built from previous evaluations…

Computation · Statistics 2025-08-26 Frederic Cerou , Patrick Heas , Mathias Rousset

Many important challenges in science and technology can be cast as optimization problems. When viewed in a statistical physics framework, these can be tackled by simulated annealing, where a gradual cooling procedure helps search for…

Disordered Systems and Neural Networks · Physics 2024-01-17 Mohamed Hibat-Allah , Estelle M. Inack , Roeland Wiersema , Roger G. Melko , Juan Carrasquilla

Atomic Layer Deposition (ALD) process development is often hindered by time-consuming and precursor-intensive tuning cycles required to identify saturation conditions. We introduce a physics-informed Bayesian active learning (BAL) framework…

Materials Science · Physics 2026-04-30 Pouyan Navabi , Christos G. Takoudis

Automatic parameter tuning methods for planning algorithms, which integrate pipeline approaches with learning-based techniques, are regarded as promising due to their stability and capability to handle highly constrained environments. While…

Robotics · Computer Science 2025-03-25 Lu Wangtao , Wei Yufei , Xu Jiadong , Jia Wenhao , Li Liang , Xiong Rong , Wang Yue

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

Computation and Language · Computer Science 2021-08-13 Zi-Yi Dou , Graham Neubig

This work presents an adaptive superfast proximal augmented Lagrangian (AS-PAL) method for solving linearly-constrained smooth nonconvex composite optimization problems. Each iteration of AS-PAL inexactly solves a possibly nonconvex…

Optimization and Control · Mathematics 2022-10-07 Arnesh Sujanani , Renato D. C. Monteiro

We study the deterministic global optimization of trained Gaussian process posterior mean functions over hyperrectangular domains. Although the posterior mean function has a compact closed-form representation, its global optimization is…

Optimization and Control · Mathematics 2026-05-05 Wei-Ting Tang , Akshay Kudva , Calvin Tsay , Joel A. Paulson

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

Methods for split conformal prediction leverage calibration samples to transform any prediction rule into a set-prediction rule that complies with a target coverage probability. Existing methods provide remarkably strong performance…

Machine Learning · Statistics 2025-10-15 Santiago Mazuelas

We consider a three-level parallelisation scheme. The second and third levels define a classical two-level parallelisation scheme and some load balancing algorithm is used to distribute tasks among processes. It is well-known that for many…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-09-24 Rima Kriauzienė , Andrej Bugajev , Raimondas Čiegis

During the preference optimization of large language models (LLMs), distribution shifts may arise between newly generated model samples and the data used to train the reward model (RM). This shift reduces the efficacy of the RM, which in…

Machine Learning · Computer Science 2025-06-11 Tianyuan Shi , Canbin Huang , Fanqi Wan , Longguang Zhong , Ziyi Yang , Weizhou Shen , Xiaojun Quan , Ming Yan
‹ Prev 1 8 9 10 Next ›