Home      Discussions      About
Join us

@cs.princeton.edu

Aug 29, 2018
By aene
Data Structures and Algorithms

Our algorithm for non-monotone DR-submodular maximization is shown in Algorithm 2. We obtain the value M by guessing like in the monotone case. Unlike the monotone case, we now include the constraints →x≤(1−ϵ)→1 into the matrix A, i.e., we solve the…

Submodular Maximization with Packing Constraints in Parallel

We consider the problem of maximizing the multilinear extension of a submodular function subject to packing constraints in parallel. For monotone fun…
Dec 02, 2014
Combinatorics
Computational Complexity

Theorem 2.8 will follow from the following theorem using a simple recursive argument.

Sylvester-Gallai for Arrangements of Subspaces

In this work we study arrangements of $k$-dimensional subspaces $V_1,\ldots,V_n \subset \mathbb{C}^\ell$. Our main result shows that, if every pair $…
Dec 08, 2011
By arora
Social and Information Networks
Data Structures and Algorithms
Physics and Society

We introduced a framework for rigorously thinking about community structure that allows (a) overlapping communities (b) includes well-studied notions such as cliques and dense subgraphs as subcases and (c) yet allows efficient algorithms for recover…

Finding Overlapping Communities in Social Networks: Toward a Rigorous…

A "community" in a social network is usually understood to be a group of nodes more densely connected with each other than with the rest of the netwo…
Jun 29, 2011
Optimization and Control
Artificial Intelligence
Machine Learning

In this paper we studied the convergence rate of AdaBoost with respect to the exponential loss. We showed upper and lower bounds for convergence rates to both an arbitrary target loss achieved by some finite combination of the weak hypotheses, as we…

The Rate of Convergence of AdaBoost

The AdaBoost algorithm was designed to combine many "weak" hypotheses that perform slightly better than random guessing into a "strong" hypothesis th…
Mar 26, 2019
By rileys
Artificial Intelligence

Q-Learning for Continuous Actions with Cross-Entropy Guided Policies

Off-Policy reinforcement learning (RL) is an important class of methods for many problem domains, such as robotics, where the cost of collecting data…
May 12, 2018
By amathur
Cryptography and Security
Human-Computer Interaction

Quantifying Users' Beliefs about Software Updates

Software updates are critical to the performance, compatibility, and security of software systems. However, users do not always install updates, leav…
Apr 08, 2015
By ehazan
Machine Learning
Computer Science and Game Theory

The Computational Power of Optimization in Online Learning

We consider the fundamental problem of prediction with expert advice where the experts are "optimizable": there is a black-box optimization oracle th…
Nov 06, 2014
Computational Geometry
Data Structures and Algorithms

Approximate k-flat Nearest Neighbor Search

Let $k$ be a nonnegative integer. In the approximate $k$-flat nearest neighbor ($k$-ANN) problem, we are given a set $P \subset \mathbb{R}^d$ of $n$ …
Jun 05, 2014
By dangar
Optimization and Control
Machine Learning

Faster Rates for the Frank-Wolfe Method over Strongly-Convex Sets

The Frank-Wolfe method (a.k.a. conditional gradient algorithm) for smooth optimization has regained much interest in recent years in the context of l…
Apr 05, 2016
By larsen
Data Structures and Algorithms
Machine Learning

Heavy hitters via cluster-preserving clustering

In turnstile $\ell_p$ $\varepsilon$-heavy hitters, one maintains a high-dimensional $x\in\mathbb{R}^n$ subject to $\texttt{update}(i,\Delta)$ causing…
Dec 26, 2017
Machine Learning

We study the problem of recovering a low-rank matrix $X^\star$ from linear measurements using an over-parameterized model. We parameterize the rank-$r$ matrix $X^\star$ by $UU^\top$ where $U\in \mathbb{R}^{d\times d}$ is a square matrix, whereas the…

Algorithmic Regularization in Over-parameterized Matrix Recovery

We study the problem of recovering a low-rank matrix $X^\star$ from linear measurements using an over-parameterized model. We parameterize the rank-$…
Jun 03, 2010
By wbajwa
Statistics Theory
Information Theory
Machine Learning

Why Gabor Frames? Two Fundamental Measures of Coherence and Their Rol…

This paper studies non-asymptotic model selection for the general case of arbitrary design matrices and arbitrary nonzero entries of the signal. In t…
Jul 19, 2015
By jm4181
Machine Learning

The Population Posterior and Bayesian Inference on Streams

Many modern data analysis problems involve inferences from streaming data. However, streaming data is not easily amenable to the standard probabilist…
Jun 11, 2019
Computation and Language
Machine Learning

Calibration, Entropy Rates, and Memory in Language Models

Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing. Towards this end…
Jul 06, 2009
By blei
Machine Learning

Visualizing Topics with Multi-Word Expressions

We describe a new method for visualizing topics, the distributions over terms that are automatically extracted from large text corpora using latent v…
Jul 14, 2010
Information Theory

Performance bounds for expander-based compressed sensing in Poisson …

This paper provides performance bounds for compressed sensing in the presence of Poisson noise using expander graphs. The Poisson noise model is appr…
Sep 30, 2009
Computational Geometry
Discrete Mathematics

Approximating Loops in a Shortest Homology Basis from Point Data

Inference of topological and geometric attributes of a hidden manifold from its point data is a fundamental problem arising in many scientific studie…
Sep 20, 2012
By chongw
Machine Learning

Variational Inference in Nonconjugate Models

Mean-field variational methods are widely used for approximate posterior inference in many probabilistic models. In a typical application, mean-field…
Apr 22, 2019
Machine Learning

Tracking and Improving Information in the Service of Fairness

As algorithmic prediction systems have become widespread, fears that these systems may inadvertently discriminate against members of underrepresented…
May 14, 2019
Signal Processing
Data Structures and Algorithms
Machine Learning
Statistics Theory

Sample Efficient Toeplitz Covariance Estimation

We study the sample complexity of estimating the covariance matrix $T$ of a distribution $\mathcal{D}$ over $d$-dimensional vectors, under the assump…
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description