English
Related papers

Related papers: On Sharing, Memoization, and Polynomial Time (Long…

200 papers

We are motivated by large scale submodular optimization problems, where standard algorithms that treat the submodular functions in the \emph{value oracle model} do not scale. In this paper, we present a model called the…

Machine Learning · Computer Science 2019-02-28 Rishabh Iyer , Jeff Bilmes

We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to…

Machine Learning · Statistics 2019-09-25 Ian Osband , Benjamin Van Roy , Daniel Russo , Zheng Wen

We study a temporal voting model where voters have dynamic preferences over a set of public chores -- projects that benefit society, but impose individual costs on those affected by their implementation. We investigate the computational…

Computer Science and Game Theory · Computer Science 2025-08-13 Edith Elkind , Tzeh Yuan Neoh , Nicholas Teh

We present a new method for inferring complexity properties for a class of programs in the form of flowcharts annotated with loop information. Specifically, our method can (soundly and completely) decide if computed values are polynomially…

Programming Languages · Computer Science 2016-07-11 Amir M. Ben-Amram , Aviad Pineles

Gradient based learning using error back-propagation (``backprop'') is a well-known contributor to much of the recent progress in AI. A less obvious, but arguably equally important, ingredient is parameter sharing - most well-known in the…

Machine Learning · Computer Science 2022-11-18 Roland Memisevic

In this paper we propose an algorithm for polynomial-time reinforcement learning in factored Markov decision processes (FMDPs). The factored optimistic initial model (FOIM) algorithm, maintains an empirical model of the FMDP in a…

Artificial Intelligence · Computer Science 2009-04-23 Istvan Szita , Andras Lorincz

The particle-in-cell numerical method of plasma physics balances a trade-off between computational cost and intrinsic noise. Inference on data produced by these simulations generally consists of binning the data to recover the particle…

Plasma Physics · Physics 2022-02-03 John Donaghy , Kai Germaschewski

In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning. We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and…

Machine Learning · Computer Science 2020-10-27 Giambattista Parascandolo , Alexander Neitz , Antonio Orvieto , Luigi Gresele , Bernhard Schölkopf

We introduce a new model of membership query (MQ) learning, where the learning algorithm is restricted to query points that are \emph{close} to random examples drawn from the underlying distribution. The learning model is intermediate…

Machine Learning · Computer Science 2013-04-19 Pranjal Awasthi , Vitaly Feldman , Varun Kanade

We prove a moment majorization principle for matrix-valued functions with domain $\{-1,1\}^{m}$, $m\in\mathbb{N}$. The principle is an inequality between higher-order moments of a non-commutative multilinear polynomial with different random…

Functional Analysis · Mathematics 2021-07-12 Steven Heilman

On the topic of probabilistic rewriting, there are several works studying both termination and confluence of different systems. While working with a lambda calculus modelling quantum computation, we found a system with probabilistic…

Logic in Computer Science · Computer Science 2022-04-11 Rafael Romero , Alejandro Díaz-Caro

Slot and van Emde Boas' weak invariance thesis states that reasonable machines can simulate each other within a polynomially overhead in time. Is $\lambda$-calculus a reasonable machine? Is there a way to measure the computational…

Logic in Computer Science · Computer Science 2014-05-15 Beniamino Accattoli , Ugo Dal Lago

Partially Observable Markov Decision Processes (POMDPs) are a natural and general model in reinforcement learning that take into account the agent's uncertainty about its current state. In the literature on POMDPs, it is customary to assume…

Machine Learning · Computer Science 2022-03-24 Noah Golowich , Ankur Moitra , Dhruv Rohatgi

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

Under the assumption of (positive) homogeneity (PH in the sequel) of the corresponding utility functions, we construct polynomial time algorithms for the weak separability, the collective consumption behavior and some related problems.…

Data Structures and Algorithms · Computer Science 2018-01-04 Alexander Shananin , Sergey Tarasov

We introduce a novel resource analysis for typed term rewrite systems based on a potential-based type system. This type system gives rise to polynomial bounds on the innermost runtime complexity. We relate the thus obtained amortised…

Logic in Computer Science · Computer Science 2014-03-17 Martin Hofmann , Georg Moser

Many reinforcement learning (RL) environments in practice feature enormous state spaces that may be described compactly by a "factored" structure, that may be modeled by Factored Markov Decision Processes (FMDPs). We present the first…

Machine Learning · Computer Science 2022-03-08 Zihao Deng , Siddartha Devic , Brendan Juba

A sound and complete algorithm for nominal unification of higher-order expressions with a recursive let is described, and shown to run in nondeterministic polynomial time. We also explore specializations like nominal letrec-matching for…

Logic in Computer Science · Computer Science 2023-06-22 Manfred Schmidt-Schauß , Temur Kutsia , Jordi Levy , Mateu Villaret , Yunus Kutz

In this paper, we consider the general scenario of resource sharing in a decentralized system when the resource rewards/qualities are time-varying and unknown to the users, and using the same resource by multiple users leads to reduced…

Machine Learning · Computer Science 2012-10-23 Cem Tekin , Mingyan Liu

Randomized protocols are procedures that incorporate probabilistic choices during their execution and they play a central role in quantum algorithms, spanning Hamiltonian simulation, noise mitigation, and measurement tasks. In practical…

Quantum Physics · Physics 2026-03-17 Davide Cugini , Touheed Anwar Atif , Yigit Subasi
‹ Prev 1 8 9 10 Next ›