English
Related papers

Related papers: ADEV: Sound Automatic Differentiation of Expected …

200 papers

The progressive hedging algorithm (PHA) is a cornerstone among algorithms for large-scale stochastic programming problems. However, its traditional implementation is hindered by some limitations, including the requirement to solve all…

Optimization and Control · Mathematics 2025-03-13 Di Zhang , Yihang Zhang , Suvrajeet Sen

We aim at computing the derivative of the solution to a parametric optimization problem with respect to the involved parameters. For a class broader than that of strongly convex functions, this can be achieved by automatic differentiation…

Optimization and Control · Mathematics 2019-10-15 Sheheryar Mehmood , Peter Ochs

In many sequence learning tasks, such as program synthesis and document summarization, a key problem is searching over a large space of possible output sequences. We propose to learn representations of the outputs that are specifically…

Machine Learning · Computer Science 2021-08-09 Joey Hong , David Dohan , Rishabh Singh , Charles Sutton , Manzil Zaheer

We introduce a physics-driven deep latent variable model (PDDLVM) to learn simultaneously parameter-to-solution (forward) and solution-to-parameter (inverse) maps of parametric partial differential equations (PDEs). Our formulation…

Machine Learning · Statistics 2023-08-09 Arnaud Vadeboncoeur , Ömer Deniz Akyildiz , Ieva Kazlauskaite , Mark Girolami , Fehmi Cirak

Computing expected predictions of discriminative models is a fundamental task in machine learning that appears in many interesting applications such as fairness, handling missing values, and data analysis. Unfortunately, computing…

Machine Learning · Computer Science 2019-11-04 Pasha Khosravi , YooJung Choi , Yitao Liang , Antonio Vergari , Guy Van den Broeck

In the context of PDE-constrained optimization theory, source identification problems traditionally entail particles emerging from an unknown source distribution inside a domain, moving according to a prescribed stochastic process,…

Optimization and Control · Mathematics 2025-08-22 Richard B. Lehoucq , Scott A. McKinley , Petr Plecháč

We consider a wide range of regularized stochastic minimization problems with two regularization terms, one of which is composed with a linear function. This optimization model abstracts a number of important applications in artificial…

Machine Learning · Computer Science 2018-02-02 Tianyi Lin , Linbo Qiao , Teng Zhang , Jiashi Feng , Bofeng Zhang

Predictive models are fundamental to engineering reliable software systems. However, designing conservative, computable approximations for the behavior of programs (static analyses) remains a difficult and error-prone process for modern…

Programming Languages · Computer Science 2011-05-10 David Van Horn , Matthew Might

Expectation propagation (EP) is a family of algorithms for performing approximate inference in probabilistic models. The updates of EP involve the evaluation of moments -- expectations of certain functions -- which can be estimated from…

Machine Learning · Statistics 2024-10-30 Jonathan So , Richard E. Turner

Stochastic variational inference offers an attractive option as a default method for differentiable probabilistic programming. However, the performance of the variational approach depends on the choice of an appropriate variational family.…

Machine Learning · Statistics 2021-02-11 Luca Ambrogioni , Kate Lin , Emily Fertig , Sharad Vikram , Max Hinne , Dave Moore , Marcel van Gerven

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Computation and Language · Computer Science 2025-11-03 Daniel Israel , Guy Van den Broeck , Aditya Grover

Probabilistic solvers for ordinary differential equations (ODEs) have emerged as an efficient framework for uncertainty quantification and inference on dynamical systems. In this work, we explain the mathematical assumptions and detailed…

Machine Learning · Statistics 2021-10-25 Nicholas Krämer , Nathanael Bosch , Jonathan Schmidt , Philipp Hennig

For probabilistic programs, it is usually not possible to automatically derive exact information about their properties, such as the distribution of states at a given program point. Instead, one can attempt to derive approximations, such as…

Programming Languages · Computer Science 2021-04-09 Di Wang , Jan Hoffmann , Thomas Reps

We study distributed stochastic convex optimization under the delayed gradient model where the server nodes perform parameter updates, while the worker nodes compute stochastic gradients. We discuss, analyze, and experiment with a setup…

Machine Learning · Statistics 2015-08-21 Suvrit Sra , Adams Wei Yu , Mu Li , Alexander J. Smola

The notion of program sensitivity (aka Lipschitz continuity) specifies that changes in the program input result in proportional changes to the program output. For probabilistic programs the notion is naturally extended to expected…

Programming Languages · Computer Science 2019-10-29 Peixin Wang , Hongfei Fu , Krishnendu Chatterjee , Yuxin Deng , Ming Xu

Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning or direct backpropagation achieve considerable success in maximizing rewards, they often suffer from…

Machine Learning · Computer Science 2026-03-09 Jaewoo Lee , Minsu Kim , Sanghyeok Choi , Inhyuck Song , Sujin Yun , Hyeongyu Kang , Woocheol Shin , Taeyoung Yun , Kiyoung Om , Jinkyoo Park

Automatic differentiation (AD) is an essential primitive for machine learning programming systems. Tangent is a new library that performs AD using source code transformation (SCT) in Python. It takes numeric functions written in a syntactic…

Mathematical Software · Computer Science 2017-11-09 Bart van Merriënboer , Alexander B. Wiltschko , Dan Moldovan

The Alternating Direction Method of Multipliers (ADMM) has been studied for years. The traditional ADMM algorithm needs to compute, at each iteration, an (empirical) expected loss function on all training examples, resulting in a…

Machine Learning · Statistics 2014-06-10 Peilin Zhao , Jinwei Yang , Tong Zhang , Ping Li

We develop nested automatic differentiation (AD) algorithms for exact inference and learning in integer latent variable models. Recently, Winner, Sujono, and Sheldon showed how to reduce marginalization in a class of integer latent variable…

Machine Learning · Statistics 2018-06-11 Daniel Sheldon , Kevin Winner , Debora Sujono

In this note we derive the backward (automatic) differentiation (adjoint [automatic] differentiation) for an algorithm containing a conditional expectation operator. As an example we consider the backward algorithm as it is used in Bermudan…

Computational Finance · Quantitative Finance 2017-07-18 Christian P. Fries