English
Related papers

Related papers: Amortized Molecular Optimization via Group Relativ…

200 papers

We propose a framework for online meta-optimization of parameters that govern optimization, called Amortized Proximal Optimization (APO). We first interpret various existing neural network optimizers as approximate stochastic proximal point…

Machine Learning · Computer Science 2022-03-02 Juhan Bae , Paul Vicol , Jeff Z. HaoChen , Roger Grosse

Optimization is a ubiquitous modeling tool and is often deployed in settings which repeatedly solve similar instances of the same problem. Amortized optimization methods use learning to predict the solutions to problems in these settings,…

Machine Learning · Computer Science 2025-10-07 Brandon Amos

Amortized analysis is a cost analysis technique for data structures in which cost is studied in aggregate: rather than considering the maximum cost of a single operation, one bounds the total cost encountered throughout a session.…

Programming Languages · Computer Science 2024-12-18 Harrison Grodin , Robert Harper

Safe active learning (AL) is a sequential scheme for learning unknown systems while respecting safety constraints during data acquisition. Existing methods often rely on Gaussian processes (GPs) to model the task and safety constraints,…

Machine Learning · Computer Science 2026-04-07 Cen-You Li , Marc Toussaint , Barbara Rakitsch , Christoph Zimmer

Learning the kernel parameters for Gaussian processes is often the computational bottleneck in applications such as online learning, Bayesian optimization, or active learning. Amortizing parameter inference over different datasets is a…

Machine Learning · Computer Science 2023-06-19 Matthias Bitzer , Mona Meister , Christoph Zimmer

Molecular design and synthesis planning are two critical steps in the process of molecular discovery that we propose to formulate as a single shared task of conditional synthetic pathway generation. We report an amortized approach to…

Machine Learning · Computer Science 2022-03-15 Wenhao Gao , Rocío Mercado , Connor W. Coley

Synthesizable molecular design (also known as synthesizable molecular optimization) is a fundamental problem in drug discovery, and involves designing novel molecular structures to improve their properties according to drug-relevant oracle…

Machine Learning · Computer Science 2026-05-07 Dannong Wang , Jintai Chen , Yingzhou Lu , Minjie Shen , Lulu Chen , Zhiding Liang , Tianfan Fu , Xiao-Yang Liu

Inferring causal structure poses a combinatorial search problem that typically involves evaluating structures with a score or independence test. The resulting search is costly, and designing suitable scores or tests that capture prior…

Machine Learning · Computer Science 2022-12-16 Lars Lorch , Scott Sussex , Jonas Rothfuss , Andreas Krause , Bernhard Schölkopf

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

Machine Learning · Computer Science 2025-10-14 Sarthak Mittal , Divyat Mahajan , Guillaume Lajoie , Mohammad Pezeshki

We study a class of algorithms for solving bilevel optimization problems in both stochastic and deterministic settings when the inner-level objective is strongly convex. Specifically, we consider algorithms based on inexact implicit…

Optimization and Control · Mathematics 2022-07-12 Michael Arbel , Julien Mairal

Modeling complex dynamical systems under varying conditions is computationally intensive, often rendering high-fidelity simulations intractable. Although reduced-order models (ROMs) offer a promising solution, current methods often struggle…

Machine Learning · Computer Science 2026-01-16 Andrew F. Ilersich , Kevin Course , Prasanth B. Nair

Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control, enabling the estimation and sampling of high-value actions. From the variational inference perspective on RL, policy networks, when…

Machine Learning · Computer Science 2021-10-26 Joseph Marino , Alexandre Piché , Alessandro Davide Ialongo , Yisong Yue

Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly…

Machine Learning · Computer Science 2026-04-27 Ofir Gordon , Lior Dikstein , Arnon Netzer , Idan Achituve , Hai Victor Habi

Traditional maximum entropy and sparsity-based algorithms for analytic continuation often suffer from the ill-posed kernel matrix or demand tremendous computation time for parameter tuning. Here we propose a neural network method by convex…

Machine Learning · Computer Science 2022-02-07 Dongchen Huang , Yi-feng Yang

Stiff dynamical systems present a challenge for machine-learning reduced-order models (ML-ROMs), as explicit time integration becomes unstable in stiff regimes while implicit integration within learning loops is computationally expensive…

Machine Learning · Computer Science 2026-03-19 Joe Standridge , Daniel Livescu , Paul Cizmas

We implement the adaptive step size scheme from the optimization methods AdaGrad and Adam in a novel variant of the Proximal Gradient Method (PGM). Our algorithm, dubbed AdaProx, avoids the need for explicit computation of the Lipschitz…

Optimization and Control · Mathematics 2020-07-06 Peter Melchior , Rémy Joseph , Fred Moolekamp

Optimization of atomic structures presents a challenging problem, due to their highly rough and non-convex energy landscape, with wide applications in the fields of drug design, materials discovery, and mechanics. Here, we present a graph…

Machine Learning · Computer Science 2023-06-21 Vaibhav Bihani , Sahil Manchanda , Srikanth Sastry , Sayan Ranu , N. M. Anoop Krishnan

This paper introduces an algorithm-agnostic approach to feature-based time series clustering via amortized neural inference. By training neural networks to approximate the optimal partitioning rule from simulated data, the proposed…

Machine Learning · Statistics 2026-05-14 Ángel López-Oriona , Ying Sun

We propose a novel adaptive, accelerated algorithm for the stochastic constrained convex optimization setting. Our method, which is inspired by the Mirror-Prox method, \emph{simultaneously} achieves the optimal rates for smooth/non-smooth…

Optimization and Control · Mathematics 2019-10-31 Ali Kavis , Kfir Y. Levy , Francis Bach , Volkan Cevher

We present HyperMorph, a learning-based strategy for deformable image registration that removes the need to tune important registration hyperparameters during training. Classical registration methods solve an optimization problem to find a…

Computer Vision and Pattern Recognition · Computer Science 2021-05-06 Andrew Hoopes , Malte Hoffmann , Bruce Fischl , John Guttag , Adrian V. Dalca
‹ Prev 1 2 3 10 Next ›