English
Related papers

Related papers: Discrete Adjoint Matching

200 papers

We propose a second order gradient based method with ADAM and RMSprop for the training of generative adversarial networks. The proposed method is fastest to obtain similar accuracy when compared to prominent second order methods. Unlike…

Machine Learning · Computer Science 2023-04-21 Sachin Kumar Danisetty , Santhosh Reddy Mylaram , Pawan Kumar

Real-world artificial intelligence (AI) systems are increasingly required to operate autonomously in dynamic, uncertain, and continuously changing environments. However, most existing AI models rely on predefined objectives, static training…

Artificial Intelligence · Computer Science 2025-11-04 Hong Su

Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the individual learning rates. Differently from existing methods, we…

Machine Learning · Computer Science 2019-02-26 Guoqiang Zhang , Kenta Niwa , W. Bastiaan Kleijn

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

Distribution matching (DM) is a versatile domain-invariant representation learning technique that has been applied to tasks such as fair classification, domain adaptation, and domain translation. Non-parametric DM methods struggle with…

Machine Learning · Computer Science 2025-06-18 Ziyu Gong , Jim Lim , David I. Inouye

In this paper, we develop a general framework to design differentially private expectation-maximization (EM) algorithms in high-dimensional latent variable models, based on the noisy iterative hard-thresholding. We derive the statistical…

Machine Learning · Statistics 2021-09-10 Zhe Zhang , Linjun Zhang

Douglas-Rachford splitting and its equivalent dual formulation ADMM are widely used iterative methods in composite optimization problems arising in control and machine learning applications. The performance of these algorithms depends on…

Optimization and Control · Mathematics 2019-06-28 Jacob H. Seidman , Mahyar Fazlyab , Victor M. Preciado , George J. Pappas

Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. Recently, dynamic mixup methods have improved previous static policies effectively…

Machine Learning · Computer Science 2023-10-24 Zicheng Liu , Siyuan Li , Ge Wang , Cheng Tan , Lirong Wu , Stan Z. Li

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Machine Learning · Computer Science 2025-09-16 Pedro Savarese

Recently, Hopfield and Krotov introduced the concept of {\em dense associative memories} [DAM] (close to spin-glasses with $P$-wise interactions in a disordered statistical mechanical jargon): they proved a number of remarkable features…

Disordered Systems and Neural Networks · Physics 2020-02-19 Francesco Alemanno , Martino Centonze , Alberto Fachechi

We introduce marginalization models (MAMs), a new family of generative models for high-dimensional discrete data. They offer scalable and flexible generative modeling by explicitly modeling all induced marginal distributions.…

Machine Learning · Computer Science 2024-10-08 Sulin Liu , Peter J. Ramadge , Ryan P. Adams

DeepSeek-R1 has successfully enhanced Large Language Model (LLM) reasoning capabilities through its rule-based reward system. While it's a ''perfect'' reward system that effectively mitigates reward hacking, such reward functions are often…

Machine Learning · Computer Science 2025-10-27 Chenxing Wei , Jiarui Yu , Ying Tiffany He , Hande Dong , Yao Shu , Fei Yu

Stochastic versions of the alternating direction method of multiplier (ADMM) and its variants play a key role in many modern large-scale machine learning problems. In this work, we introduce a unified algorithmic framework called…

Optimization and Control · Mathematics 2024-04-23 Chris Junchi Li

We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics, and operations…

Machine Learning · Computer Science 2025-12-18 Hanqing Jin , Renyuan Xu , Yanzhao Yang

In this paper, we develop a symmetric accelerated stochastic Alternating Direction Method of Multipliers (SAS-ADMM) for solving separable convex optimization problems with linear constraints. The objective function is the sum of a possibly…

Optimization and Control · Mathematics 2021-12-21 Jianchao Bai , Deren Han , Hao Sun , Hongchao Zhang

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same…

Machine Learning · Computer Science 2025-04-29 Zhaoyang Wang , Weilei He , Zhiyuan Liang , Xuchao Zhang , Chetan Bansal , Ying Wei , Weitong Zhang , Huaxiu Yao

Recent advances in test-time alignment methods, such as Best-of-N sampling, offer a simple and effective way to steer language models (LMs) toward preferred behaviors using reward models (RM). However, these approaches can be…

Computation and Language · Computer Science 2026-03-16 Vinod Raman , Hilal Asi , Satyen Kale

We describe a general approach for maximum a posteriori (MAP) inference in a class of discrete-continuous factor graphs commonly encountered in robotics applications. While there are openly available tools providing flexible and easy-to-use…

Robotics · Computer Science 2022-11-21 Kevin J. Doherty , Ziqi Lu , Kurran Singh , John J. Leonard

Deep neural network learning can be formulated as a non-convex optimization problem. Existing optimization algorithms, e.g., Adam, can learn the models fast, but may get stuck in local optima easily. In this paper, we introduce a novel…

Machine Learning · Computer Science 2019-03-12 Jiawei Zhang , Fisher B. Gouza

The Linear Parameter Varying Dynamical System (LPV-DS) is an effective approach that learns stable, time-invariant motion policies using statistical modeling and semi-definite optimization to encode complex motions for reactive robot…

Robotics · Computer Science 2024-03-26 Sunan Sun , Haihui Gao , Tianyu Li , Nadia Figueroa