English
Related papers

Related papers: The Entropy of Backwards Analysis

200 papers

A criterion for pruning parameters from N-gram backoff language models is developed, based on the relative entropy between the original and the pruned model. It is shown that the relative entropy resulting from pruning a single N-gram can…

Computation and Language · Computer Science 2007-05-23 A. Stolcke

In backward error analysis, an approximate solution to an equation is compared to the exact solution to a nearby modified equation. In numerical ordinary differential equations, the two agree up to any power of the step size. If the…

Numerical Analysis · Mathematics 2022-07-21 Robert I McLachlan , Christian Offen

Neural networks are becoming increasingly prevalent in software, and it is therefore important to be able to verify their behavior. Because verifying the correctness of neural networks is extremely challenging, it is common to focus on the…

Machine Learning · Computer Science 2019-02-19 Ravi Mangal , Aditya V. Nori , Alessandro Orso

Previous compact representations of permutations have focused on adding a small index on top of the plain data $<\pi(1), \pi(2),...\pi(n)>$, in order to efficiently support the application of the inverse or the iterated permutation. In this…

Data Structures and Algorithms · Computer Science 2011-08-23 Jérémy Barbay , Gonzalo Navarro

Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been proposed as a new paradigm to approximate the posterior by a…

Machine Learning · Computer Science 2018-03-08 Francesco Locatello , Rajiv Khanna , Joydeep Ghosh , Gunnar Rätsch

Low-rank approximation of a matrix by means of random sampling has been consistently efficient in its empirical studies by many scientists who applied it with various sparse and structured multipliers, but adequate formal support for this…

Numerical Analysis · Mathematics 2016-06-07 Victor Y. Pan , Liang Zhao

Variational inference approximates the posterior distribution of a probabilistic model with a parameterized density by maximizing a lower bound for the model evidence. Modern solutions fit a flexible approximation with stochastic gradient…

Machine Learning · Statistics 2017-07-13 Joseph Sakaya , Arto Klami

From the output produced by a memoryless deletion channel from a uniformly random input of known length $n$, one obtains a posterior distribution on the channel input. The difference between the Shannon entropy of this distribution and that…

Information Theory · Computer Science 2018-08-01 Arash Atashpendar , David Mestel , A. W. Roscoe , Peter Y. A. Ryan

Comparison-based algorithms are algorithms for which the execution of each operation is solely based on the outcome of a series of comparisons between elements. Comparison-based computations can be naturally represented via the following…

Data Structures and Algorithms · Computer Science 2020-11-17 Michel Schellekens

In adaptive data analysis, a mechanism gets $n$ i.i.d. samples from an unknown distribution $D$, and is required to provide accurate estimations to a sequence of adaptively chosen statistical queries with respect to $D$. Hardt and Ullman…

Machine Learning · Computer Science 2023-11-07 Kobbi Nissim , Uri Stemmer , Eliad Tsfadia

Least-squares approximation is one of the most important methods for recovering an unknown function from data. While in many applications the data is fixed, in many others there is substantial freedom to choose where to sample. In this…

Machine Learning · Statistics 2025-08-11 Ben Adcock

Using Bayes's theorem, we derive a unit-wise recurrence as well as a backward recursion similar to the forward-backward algorithm. The resulting Bayesian recurrent units can be integrated as recurrent neural networks within deep learning…

Machine Learning · Statistics 2022-09-29 Alexandre Bittar , Philip N. Garner

The following note proves that conditional entropy of a sequence is almost time-reversal invariant, specifically they only differ by a small constant factor dependent only upon the forward and backward models that the entropies are being…

Information Theory · Computer Science 2024-04-04 Adam Wang

Consider a regression problem where the learner is given a large collection of $d$-dimensional data points, but can only query a small subset of the real-valued labels. How many queries are needed to obtain a $1+\epsilon$ relative error…

Machine Learning · Computer Science 2021-06-29 Xue Chen , Michał Dereziński

A sufficient and necessary condition ensuring that the backward shift operator on the K\"{o}the sequence space admits an invariant distributionally $\varepsilon$-scrambled set for some $\varepsilon>0$ is obtained, improving the main results…

Dynamical Systems · Mathematics 2019-04-23 Xinxing Wu , Yang Luo

Statistical inverse learning aims at recovering an unknown function $f$ from randomly scattered and possibly noisy point evaluations of another function $g$, connected to $f$ via an ill-posed mathematical model. In this paper we blend…

Statistics Theory · Mathematics 2024-01-22 Tapio Helin

Mixture distributions are extensively used as a modeling tool in diverse areas from machine learning to communications engineering to physics, and obtaining bounds on the entropy of probability distributions is of fundamental importance in…

Information Theory · Computer Science 2022-12-05 James Melbourne , Saurav Talukdar , Shreyas Bhaban , Mokshay Madiman , Murti V. Salapaka

We develop new techniques for proving lower bounds on the least singular value of random matrices with limited randomness. The matrices we consider have entries that are given by polynomials of a few underlying base random variables. This…

Data Structures and Algorithms · Computer Science 2025-09-29 Aditya Bhaskara , Eric Evert , Vaidehi Srinivas , Aravindan Vijayaraghavan

This paper proposes a new Sequential Monte Carlo algorithm to perform online estimation in the context of state space models when either the transition density of the latent state or the conditional likelihood of an observation given a…

Applications · Statistics 2021-05-10 Alice Martin , Marie-Pierre Etienne , Pierre Gloaguen , Sylvain Le Corff , Jimmy Olsson

In this paper, we present perturbation analysis and randomized algorithms for the total least squares (TLS) problems. We derive the perturbation bound and check its sharpness by numerical experiments. Motivated by the recently popular…

Numerical Analysis · Mathematics 2014-11-12 Pengpeng Xie , Yimin Wei , Hua Xiang
‹ Prev 1 3 4 5 6 7 10 Next ›