English
Related papers

Related papers: Does This Gradient Spark Joy?

200 papers

In a typical school choice application, the students have strict preferences over the schools while the schools have coarse priorities over the students based on their distance and their enrolled siblings. The outcome of a centralized…

Computer Science and Game Theory · Computer Science 2026-02-12 Haris Aziz , Péter Biró , Gergely Csáji , Tom Demeulemeester

Pricing financial derivatives on quantum computers typically includes quantum arithmetic components which contribute heavily to the quantum resources required by the corresponding circuits. In this manuscript, we introduce a method based on…

Quantum Physics · Physics 2024-05-01 Nikitas Stamatopoulos , William J. Zeng

In this paper, we explore how directly pretraining a value model simplifies and stabilizes reinforcement learning from human feedback (RLHF). In reinforcement learning, value estimation is the key to policy optimization, distinct from…

Machine Learning · Computer Science 2026-01-27 Chenghua Huang , Lu Wang , Fangkai Yang , Pu Zhao , Zhixu Li , Qingwei Lin , Dongmei Zhang , Saravan Rajmohan , Qi Zhang

Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the \emph{alignment tax}. We study this trade-off through the…

Machine Learning · Computer Science 2026-05-13 Guanglong Sun , Siyuan Zhang , Liyuan Wang , Jun Zhu , Hang Su , Yi Zhong

We propose a cross-fitted debiasing device for policy learning from offline data. A key consequence of the resulting learning principle is $\sqrt N$ regret even for policy classes with complexity greater than Donsker, provided a…

Machine Learning · Statistics 2026-04-06 Aurelien Bibaut , Houssam Zenati , Thibaud Rahier , Nathan Kallus

Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully…

Machine Learning · Computer Science 2020-05-26 Kamyar Azizzadenesheli , Yisong Yue , Animashree Anandkumar

This article is in the context of gradient compression. Gradient compression is a popular technique for mitigating the communication bottleneck observed when training large machine learning models in a distributed manner using…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-08-24 Tharindu Adikari

In unconstrained optimisation on an Euclidean space, to prove convergence in Gradient Descent processes (GD) $x_{n+1}=x_n-\delta _n \nabla f(x_n)$ it usually is required that the learning rates $\delta _n$'s are bounded: $\delta _n\leq…

Optimization and Control · Mathematics 2020-01-09 Tuyen Trung Truong

In this paper, we analyze the optimization landscape of gradient descent methods for static output feedback (SOF) control of discrete-time linear time-invariant systems with quadratic cost. The SOF setting can be quite common, for example,…

Optimization and Control · Mathematics 2023-10-31 Jingliang Duan , Jie Li , Shengbo Eben Li , Lin Zhao

This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar energy function whose gradient is the denoising field. We establish that under…

Robotics · Computer Science 2026-05-12 Yanbiao Ji , Qiuchang Li , Yuting Hu , Shaokai Wu , Wenyuan Xie , Guodong Zhang , Qicheng He , Deyi Ji , Yue Ding , Hongtao Lu

We consider a retailer running a switchback experiment for the price of a single product, with infinite supply. In each period, the seller chooses a price $p$ from a set of predefined prices that consist of a reference price and a few…

Computer Science and Game Theory · Computer Science 2024-10-22 Yifan Wu , Ramesh Johari , Vasilis Syrgkanis , Gabriel Y. Weintraub

Backpropagation is the default learning rule for artificial neural networks and is often treated as the settled approach whenever differentiability is available. In this work, we revisit this convention through a theoretical lens of sample…

Machine Learning · Statistics 2026-05-28 Yibo Jacky Zhang , Zeyu Tang , Sanmi Koyejo

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

Machine Learning · Computer Science 2019-11-13 Mattis Manfred Kämmerer

Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsampling, Gaussian perturbation, and privacy accounting. Classical DP-SGD releases a noisy…

Cryptography and Security · Computer Science 2026-05-12 Mohammad Partohaghighi , Roummel Marcia

Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even "fast" attacks such as FGSM remain throughput-limited by the cost of a backward pass. We introduce a…

Machine Learning · Computer Science 2026-05-15 Kamil Ciosek , Aleksandr V. Petrov , Nicolò Felicioni , Konstantina Palla

We consider contextual bandit learning under distribution shift when reward vectors are ordered according to a given preference cone. We propose an adaptive-discretization and optimistic elimination based policy that self-tunes to the…

Machine Learning · Computer Science 2025-08-25 Apurv Shukla , P. R. Kumar

Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions…

Machine Learning · Computer Science 2024-10-10 Junlin Wu , Jiongxiao Wang , Chaowei Xiao , Chenguang Wang , Ning Zhang , Yevgeniy Vorobeychik

We consider deep deterministic policy gradient (DDPG) in the context of reinforcement learning with sparse rewards. To enhance exploration, we introduce a search procedure, \emph{${\epsilon}{t}$-greedy}, which generates exploratory options…

Machine Learning · Computer Science 2026-02-18 Ehsan Futuhi , Shayan Karimi , Chao Gao , Martin Müller

We introduce ProxSkip -- a surprisingly simple and provably efficient method for minimizing the sum of a smooth ($f$) and an expensive nonsmooth proximable ($\psi$) function. The canonical approach to solving such problems is via the…

Machine Learning · Computer Science 2023-03-27 Konstantin Mishchenko , Grigory Malinovsky , Sebastian Stich , Peter Richtárik

While real quantum devices have been increasingly used to conduct research focused on achieving quantum advantage or quantum utility in recent years, executing deep quantum circuits or performing quantum machine learning with large-scale…

Quantum Physics · Physics 2026-04-06 Yoshiaki Kawase
‹ Prev 1 3 4 5 6 7 10 Next ›