
Efficient CoarsetoFine NonLocal Module for the Detection of Small Objects
An image is not just a collection of objects, but rather a graph where e...
read it

VQA with no questionsanswers training
Methods for teaching machines to answer visual questions have made signi...
read it

What can human minimal videos tell us about dynamic recognition models?
In human vision objects and their parts can be visually recognized from ...
read it

Expecting the Unexpected: Developing AutonomousSystem Design Principles for Reacting to Unpredicted Events and Conditions
When developing autonomous systems, engineers and other stakeholders mak...
read it

Towards a Computer Vision Particle Flow
In high energy physics experiments Particle Flow (PFlow) algorithms are ...
read it

Ensemble Wrapper Subsampling for Deep Modulation Classification
Subsampling of received wireless signals is important for relaxing hardw...
read it

Is Local SGD Better than Minibatch SGD?
We study local SGD (also known as parallel SGD and federated averaging),...
read it

How Good is SGD with Random Shuffling?
We study the performance of stochastic gradient descent (SGD) on smooth ...
read it

Understand, Compose and Respond  Answering Visual Questions by a Composition of Abstract Procedures
An image related question defines a specific visual task that is require...
read it

ImageNettrained deep neural network exhibits illusionlike response to the Scintillating Grid
Deep neural network (DNN) models for computer vision are now capable of ...
read it

Unfolding Neural Networks for Compressive Multichannel Blind Deconvolution
We propose a learnedstructured unfolding neural network for the problem...
read it

DepthWidth Tradeoffs in Approximating Natural Functions with Neural Networks
We provide several new depthbased separation results for feedforward n...
read it

DistributionSpecific Hardness of Learning Neural Networks
Although neural networks are routinely and successfully trained in pract...
read it

Efficient Representation of LowDimensional Manifolds using Deep Networks
We consider the ability of deep neural networks to represent data that l...
read it

The Power of Depth for Feedforward Neural Networks
We show that there is a simple (approximately radial) function on ^d, ex...
read it

Limitations on VarianceReduction and Acceleration Schemes for Finite Sum Optimization
We study the conditions under which one is able to efficiently apply var...
read it

Bandit Regret Scaling with the Effective Loss Range
We study how the regret guarantees of nonstochastic multiarmed bandits ...
read it

Unsupervised Ensemble Regression
Consider a regression problem where there is no labeled data and the onl...
read it

Do You See What I Mean? Visual Resolution of Linguistic Ambiguities
Understanding language goes hand in hand with the ability to integrate c...
read it

Spurious Local Minima are Common in TwoLayer ReLU Neural Networks
We consider the optimization problem associated with training simple ReL...
read it

Human perception in computer vision
Computer vision has made remarkable progress in recent years. Deep neura...
read it

Graph Approximation and Clustering on a Budget
We consider the problem of learning from a similarity matrix (such as sp...
read it

WithoutReplacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization
Stochastic gradient methods for machine learning and optimization proble...
read it

MultiPlayer Bandits  a Musical Chairs Approach
We consider a variant of the stochastic multiarmed bandit problem, wher...
read it

On the Quality of the Initial Basin in Overspecified Neural Networks
Deep learning, in the form of artificial neural networks, has achieved r...
read it

Convergence of Stochastic Gradient Descent for PCA
We consider the problem of principal component analysis (PCA) in a strea...
read it

An Algorithm for Training Polynomial Networks
We consider deep neural networks, in which the output of each node is a ...
read it

Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity
We study the convergence properties of the VRPCA algorithm introduced b...
read it

An Optimal Algorithm for Bandit and ZeroOrder Convex Optimization with TwoPoint Feedback
We consider the closely related problems of bandit convex optimization w...
read it

Communication Complexity of Distributed Convex Learning and Optimization
We study the fundamental limits to communicationefficient distributed m...
read it

Action Classification via Concepts and Attributes
Classes in natural images tend to follow long tail distributions. This i...
read it

On the Complexity of Learning with Kernels
A wellrecognized limitation of kernel learning is the requirement to ha...
read it

Attribute Efficient Linear Regression with DataDependent Sampling
In this paper we analyze a budgeted learning setting, in which the learn...
read it

Textual Features for Programming by Example
In Programming by Example, a system attempts to infer a program from inp...
read it

Nonstochastic MultiArmed Bandits with GraphStructured Feedback
We present and study a partialinformation model of online learning, whe...
read it

On the Optimality of Averaging in Distributed Statistical Learning
A common approach to statistical learning with bigdata is to randomly s...
read it

Facespace Action Recognition by FaceObject Interactions
Action recognition in still images has seen major improvement in recent ...
read it

HandObject Interaction and Precise Localization in Transitive Action Recognition
Action recognition in still images has seen major improvement in recent ...
read it

Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimation
Many machine learning approaches are characterized by information constr...
read it

A Quantitative Version of the GibbardSatterthwaite Theorem for Three Alternatives
The GibbardSatterthwaite theorem states that every nondictatorial elec...
read it

Efficient Classification for Metric Data
Recent advances in largemargin classification of data residing in gener...
read it

Adaptive Metric Dimensionality Reduction
We study adaptive datadependent dimensionality reduction in the context...
read it

On the Complexity of Bandit and DerivativeFree Stochastic Convex Optimization
The problem of stochastic convex optimization with bandit feedback (in t...
read it

Why are images smooth?
It is a well observed phenomenon that natural images are smooth, in the ...
read it

Stable Camera Motion Estimation Using Convex Programming
We study the inverse problem of estimating n locations t_1, ..., t_n (up...
read it

Manifold Learning: The Price of Normalization
We analyze the performance of a class of manifoldlearning algorithms th...
read it

From Shading to Local Shape
We develop a framework for extracting a concise representation of the sh...
read it

A Unified Multiscale Framework for Discrete Energy Minimization
Discrete energy minimization is a ubiquitous task in computer vision, ye...
read it

Linear versus Nonlinear Acquisition of StepFunctions
We address in this paper the following two closely related problems: 1...
read it

Approximation of Polyhedral Surface Uniformization
We present a constructive approach for approximating the conformal map (...
read it
Weizmann Institute of Science
The Weizmann Institute of Science is a public research university in Rehovot, Israel, established in 1934, 14 years before the State of Israel.