English
Related papers

Related papers: Stochastic Reconfiguration with Warm-Started SVD

200 papers

Recent years have witnessed the popularity of using rank minimization as a regularizer for various signal processing and machine learning problems. As rank minimization problems are often converted to nuclear norm minimization (NNM)…

Numerical Analysis · Computer Science 2010-12-30 Zhouchen Lin , Siming Wei

We revisit the use of Stochastic Gradient Descent (SGD) for solving convex optimization problems that serve as highly popular convex relaxations for many important low-rank matrix recovery problems such as \textit{matrix completion},…

Machine Learning · Computer Science 2020-06-16 Dan Garber

We show that the standard Lanczos algorithm can be efficiently implemented statistically and self consistently improved, using the stochastic reconfigurat ion method, which has been recently introduced to stabilize the Monte Carlo sign…

Strongly Correlated Electrons · Physics 2009-02-05 S. Sorella

LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade model accuracy. Stochastic Rounding (SR) has emerged as a…

Machine Learning · Computer Science 2025-11-04 Taowen Liu , Marta Andronic , Deniz Gündüz , George A. Constantinides

In this paper, we propose a novel warm restart technique using a new logarithmic step size for the stochastic gradient descent (SGD) approach. For smooth and non-convex functions, we establish an $O(\frac{1}{\sqrt{T}})$ convergence rate for…

Machine Learning · Computer Science 2024-04-02 M. Soheil Shamaee , S. Fathi Hafshejani , Z. Saeidian

Quantum Monte Carlo (QMC) methods are often used to calculate properties of many body quantum systems. The main cost of many QMC methods, for example the variational Monte Carlo (VMC) method, is in constructing a sequence of Slater matrices…

Strongly Correlated Electrons · Physics 2011-05-10 Kapil Ahuja , Bryan K. Clark , Eric de Sturler , David M. Ceperley , Jeongnim Kim

mVMC (many-variable Variational Monte Carlo) is an open-source software based on the variational Monte Carlo method applicable for a wide range of Hamiltonians for interacting fermion systems. In mVMC, we introduce more than ten thousands…

This paper presents a goal-oriented a posteriori error estimation framework for linear functionals in the stabilized finite element discretization of the stationary convection-diffusion-reaction (CDR) equation. The theoretical framework for…

Numerical Analysis · Mathematics 2025-05-07 Sheraz Ahmed Khan , Ramon Codina , Hauke Gravenkamp

Variational methods are highly valuable computational tools for solving high-dimensional quantum systems. In this paper, we explore the effectiveness of three variational methods: the density matrix renormalization group (DMRG), Boltzmann…

Quantum Physics · Physics 2024-04-18 Daming Li

Parameter shift rules (PSRs) are key techniques for efficient gradient estimation in variational quantum eigensolvers (VQEs). In this paper, we propose its Bayesian variant, where Gaussian processes with appropriate kernels are used to…

Machine Learning · Computer Science 2026-05-07 Samuele Pedrielli , Christopher J. Anders , Lena Funcke , Karl Jansen , Kim A. Nicoli , Shinichi Nakajima

Variational Monte Carlo (VMC) is a powerful and fast-growing method for optimizing and evolving parameterized many-body wave functions, especially with modern neural-network quantum states. In practice, however, the stochastic estimators…

Strongly Correlated Electrons · Physics 2026-03-20 Zhou-Quan Wan , Roeland Wiersema , Shiwei Zhang

The multi-configurational self-consistent field theory is considered the standard starting point for almost all multireference approaches required for strongly-correlated molecular problems. The limitation of the approach is generally given…

Chemical Physics · Physics 2015-10-14 Robert E. Thomas , Qiming Sun , Ali Alavi , George H. Booth

Reinforcement learning is a powerful framework aiming to determine optimal behavior in highly complex decision-making scenarios. This objective can be achieved using policy iteration, which requires to solve a typically large linear system…

Modeling and predicting the dynamics of complex multiscale systems remains a significant challenge due to their inherent nonlinearities and sensitivity to initial conditions, as well as limitations of traditional machine learning methods…

Machine Learning · Computer Science 2025-10-23 Elias Al Ghazal , Jad Mounayer , Beatriz Moya , Sebastian Rodriguez , Chady Ghnatios , Francisco Chinesta

We present a variational method for online state estimation and parameter learning in state-space models (SSMs), a ubiquitous class of latent variable models for sequential data. As per standard batch variational techniques, we use…

Machine Learning · Statistics 2022-06-16 Andrew Campbell , Yuyang Shi , Tom Rainforth , Arnaud Doucet

Singular value decomposition (SVD) is one of the most popular compression methods that approximate a target matrix with smaller matrices. However, standard SVD treats the parameters within the matrix with equal importance, which is a simple…

Computation and Language · Computer Science 2022-12-19 Ting Hua , Yen-Chang Hsu , Felicity Wang , Qian Lou , Yilin Shen , Hongxia Jin

Stochastic First-Order (SFO) methods have been a cornerstone in addressing a broad spectrum of modern machine learning (ML) challenges. However, their efficacy is increasingly questioned, especially in large-scale applications where…

Machine Learning · Computer Science 2024-08-01 Di Zhang , Suvrajeet Sen

Solving the ground state of quantum many-body systems remains a fundamental challenge in physics and chemistry. Recent advancements in quantum hardware have opened new avenues for addressing this challenge. Inspired by the quantum-enhanced…

Quantum Physics · Physics 2025-06-10 Longfei Chang , Zhendong Li , Wei-Hai Fang

Popular parameter-efficient fine-tuning (PEFT) methods, such as LoRA and its variants, freeze pre-trained model weights \(W\) and inject learnable matrices \(\Delta W\). These \(\Delta W\) matrices are structured for efficient…

Regularized empirical risk minimization (rERM) has become important in data-intensive fields such as genomics and advertising, with stochastic gradient methods typically used to solve the largest problems. However, ill-conditioned…

Machine Learning · Statistics 2025-01-28 Jingruo Sun , Zachary Frangella , Madeleine Udell