English
Related papers

Related papers: Automatic Differentiation in PCF

200 papers

How does one compile derivatives of tensor programs, such that the resulting code is purely functional (hence easier to optimize and parallelize) and provably efficient relative to the original program? We show that naively differentiating…

Programming Languages · Computer Science 2020-10-01 Gilbert Bernstein , Michael Mara , Tzu-Mao Li , Dougal Maclaurin , Jonathan Ragan-Kelley

A discounted-sum automaton (NDA) is a nondeterministic finite automaton with edge weights, valuing a run by the discounted sum of visited edge weights. More precisely, the weight in the i-th position of the run is divided by $\lambda^i$,…

Formal Languages and Automata Theory · Computer Science 2015-07-01 Udi Boker , Thomas A. Henzinger

Automatic differentiation is a key component in deep learning. This topic is well studied and excellent surveys such as Baydin et al. (2018) have been available to clearly describe the basic concepts. Further, sophisticated implementations…

Machine Learning · Computer Science 2024-12-18 Yu-Hsueh Fang , He-Zhe Lin , Jie-Jyun Liu , Chih-Jen Lin

The Adaptive Momentum Estimation (Adam) algorithm is highly effective in training various deep learning tasks. Despite this, there's limited theoretical understanding for Adam, especially when focusing on its vanilla form in non-convex…

Optimization and Control · Mathematics 2025-02-25 Yusu Hong , Junhong Lin

We analyse the convergence of an approximate, fully inexact, ADMM algorithm under additive, deterministic and probabilistic error models. We consider the generalized ADMM scheme that is derived from generalized Lagrangian penalty with…

Optimization and Control · Mathematics 2022-10-06 Anis Hamadouche , Yun Wu , Andrew M. Wallace , Joao F. C. Mota

We consider the class of counting problems,i.e. functions in $\#$P, which are self reducible, and have easy decision version, i.e. for every input it is easy to decide if the value of the function $f(x)$ is zero. For example,…

Computational Complexity · Computer Science 2016-11-08 Eleni Bakali

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

Optimization and Control · Mathematics 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

Several algorithms in computer algebra involve the computation of a power series solution of a given ordinary differential equation. Over finite fields, the problem is often lifted in an approximate $p$-adic setting to be well-posed. This…

Symbolic Computation · Computer Science 2023-06-12 Pierre Lairez , Tristan Vaccon

This paper introduces an upper bound on the absolute difference between: (a) the cumulative distribution function (CDF) of the sum of a finite number of independent and identically distributed random variables with finite absolute third…

Information Theory · Computer Science 2020-07-22 Dadja Anade , Jean-Marie Gorce , Philippe Mary , Samir Perlaza

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

The problem of low-tubal-rank tensor estimation is a fundamental task with wide applications across high-dimensional signal processing, machine learning, and image science. Traditional approaches tackle such a problem by performing tensor…

Machine Learning · Computer Science 2025-12-24 Zhiyu Liu , Zhi Han , Yandong Tang , Jun Fan , Yao Wang

We extend JAX with the capability to automatically differentiate higher-order functions (functionals and operators). By representing functions as a generalization of arrays, we seamlessly use JAX's existing primitive system to implement…

Programming Languages · Computer Science 2024-01-30 Min Lin

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

Automated program repair (APR) attempts to generate correct patches and has drawn wide attention from both academia and industry in the past decades. However, APR is continuously struggling with the patch overfitting issue due to the weak…

Software Engineering · Computer Science 2026-04-07 Quanjun Zhang , Haichuan Hu , Chunrong Fang , Ye Shang , Tao Zheng , Zhenyu Chen , Yun Yang , Liang Xiao

For a class L of languages let PDL[L] be an extension of Propositional Dynamic Logic which allows programs to be in a language of L rather than just to be regular. If L contains a non-regular language, PDL[L] can express non-regular…

Logic in Computer Science · Computer Science 2011-06-08 Markus Latte

We prove an impossibility result for conditional Probably Approximately Correct (PAC)-efficient reasoning in large language models. While recent work has established marginal PAC efficiency guarantees for composite models that switch…

Machine Learning · Statistics 2025-12-04 Hao Zeng

No single Automatic Differentiation (AD) system is the optimal choice for all problems. This means informed selection of an AD system and combinations can be a problem-specific variable that can greatly impact performance. In the Julia…

Mathematical Software · Computer Science 2022-02-08 Frank Schäfer , Mohamed Tarek , Lyndon White , Chris Rackauckas

We present a probabilistic version of PCF, a well-known simply typed universal functional language. The type hierarchy is based on a single ground type of natural numbers. Even if the language is globally call-by-name, we allow a…

Logic in Computer Science · Computer Science 2015-11-05 Thomas Ehrhard , Michele Pagani , Christine Tasson

In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives. Despite the popularity and efficiency of the Adam algorithm in training deep neural…

Optimization and Control · Mathematics 2023-11-08 Haochuan Li , Alexander Rakhlin , Ali Jadbabaie

Probabilistic automata are an extension of nondeterministic finite automata in which transitions are annotated with probabilities. Despite its simplicity, this model is very expressive and many of the associated algorithmic questions are…

Formal Languages and Automata Theory · Computer Science 2022-05-20 Nathanaël Fijalkow , Cristian Riveros , James Worrell