English
Related papers

Related papers: Faster Convergence with Multiway Preferences

200 papers

We address the problem of \emph{convex optimization with dueling feedback}, where the goal is to minimize a convex function given a weaker form of \emph{dueling} feedback. Each query consists of two points and the dueling feedback returns a…

Optimization and Control · Mathematics 2022-10-07 Aadirupa Saha , Tomer Koren , Yishay Mansour

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts…

Computation and Language · Computer Science 2025-04-16 Zhihao Xu , Yongqi Tong , Xin Zhang , Jun Zhou , Xiting Wang

We study the problems of distributed online and bandit convex optimization against an adaptive adversary. We aim to minimize the average regret on $M$ machines working in parallel over $T$ rounds with $R$ intermittent communications.…

Machine Learning · Computer Science 2023-11-30 Kumar Kshitij Patel , Lingxiao Wang , Aadirupa Saha , Nati Sebro

In interactive systems, feedback is often provided in the form of preference between queried options rather than precise scores, which motivates optimization methods to learn from such comparisons. In this work, we propose a…

Optimization and Control · Mathematics 2025-12-23 Siyi Wang , Zifan Wang , Karl Henrik Johanssson

Motivated by the stringent safety requirements that are often present in real-world applications, we study a safe online convex optimization setting where the player needs to simultaneously achieve sublinear regret and zero constraint…

Machine Learning · Computer Science 2024-07-17 Spencer Hutchinson , Mahnoosh Alizadeh

We consider strongly convex-concave minimax problems in the federated setting, where the communication constraint is the main bottleneck. When clients are arbitrarily heterogeneous, a simple Minibatch Mirror-prox achieves the best…

Machine Learning · Computer Science 2021-02-15 Charlie Hou , Kiran K. Thekumparampil , Giulia Fanti , Sewoong Oh

Convex optimization with feedback is a framework where a learner relies on iterative queries and feedback to arrive at the minimizer of a convex function. It has gained considerable popularity thanks to its scalability in large-scale…

Machine Learning · Statistics 2021-10-26 Jiaming Xu , Kuang Xu , Dana Yang

We consider the problem of adversarial bandit convex optimization, that is, online learning over a sequence of arbitrary convex loss functions with only one function evaluation for each of them. While all previous works assume known and…

Machine Learning · Computer Science 2022-02-15 Haipeng Luo , Mengxiao Zhang , Peng Zhao

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

Machine Learning · Computer Science 2026-02-03 Luca Viano , Ruida Zhou , Yifan Sun , Mahdi Namazifar , Volkan Cevher , Shoham Sabach , Mohammad Ghavamzadeh

Frequently, when dealing with many machine learning models, optimization problems appear to be challenging due to a limited understanding of the constructions and characterizations of the objective functions in these problems. Therefore,…

Optimization and Control · Mathematics 2024-11-27 A. V. Gasnikov , M. S. Alkousa , A. V. Lobanov , Y. V. Dorn , F. S. Stonyakin , I. A. Kuruzov , S. R. Singh

Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a problem as a semivectorial bilevel optimization problem, whose…

Optimization and Control · Mathematics 2025-04-07 Lisha Chen , Quan Xiao , Ellen Hidemi Fukuda , Xinyi Chen , Kun Yuan , Tianyi Chen

We consider the fundamental problem in non-convex optimization of efficiently reaching a stationary point. In contrast to the convex case, in the long history of this basic problem, the only known theoretical results on first-order…

Optimization and Control · Mathematics 2016-08-26 Zeyuan Allen-Zhu , Elad Hazan

We consider the problem of minimizing a convex function over the intersection of finitely many simple sets which are easy to project onto. This is an important problem arising in various domains such as machine learning. The main difficulty…

Optimization and Control · Mathematics 2017-10-19 Achintya Kundu , Francis Bach , Chiranjib Bhattacharyya

Communication has been seen as a significant bottleneck in industrial applications over large-scale networks. To alleviate the communication burden, sign-based optimization algorithms have gained popularity recently in both industrial and…

Optimization and Control · Mathematics 2021-09-07 Xiuxian Li , Kuo-Yi Lin , Li Li , Yiguang Hong , Jie Chen

We propose a novel continuous-time algorithm for inequality-constrained convex optimization inspired by proportional-integral control. Unlike the popular primal-dual gradient dynamics, our method includes a proportional term to control the…

Optimization and Control · Mathematics 2024-09-12 V. Cerone , S. M. Fosson , S. Pirrera , D. Regruto

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

Machine Learning · Computer Science 2023-11-02 Han Shao , Lee Cohen , Avrim Blum , Yishay Mansour , Aadirupa Saha , Matthew R. Walter

We consider the closely related problems of bandit convex optimization with two-point feedback, and zero-order stochastic convex optimization with two function evaluations per round. We provide a simple algorithm and analysis which is…

Machine Learning · Computer Science 2015-08-03 Ohad Shamir

The existing machine learning algorithms for minimizing the convex function over a closed convex set suffer from slow convergence because their learning rates must be determined before running them. This paper proposes two machine learning…

Optimization and Control · Mathematics 2019-09-02 Kazuhiro Hishinuma , Hideaki Iiduka

We propose a variant of consensus-based optimization (CBO) algorithms, controlled-CBO, which introduces a feedback control term to improve convergence towards global minimizers of non-convex functions in multiple dimensions. The feedback…

Optimization and Control · Mathematics 2025-07-29 Yuyang Huang , Michael Herty , Dante Kalise , Nikolas Kantas

Many real-world applications are characterized by a number of conflicting performance measures. As optimizing in a multi-objective setting leads to a set of non-dominated solutions, a preference function is required for selecting the…

Machine Learning · Computer Science 2017-04-24 Audrey Durand , Christian Gagné
‹ Prev 1 2 3 10 Next ›