
Multiclass nonAdversarial Image Synthesis, with Application to Classification from Very Small Sample
The generation of synthetic images is currently being dominated by Gener...
read it

Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
Domain generalization is the problem of machine learning when the traini...
read it

An InformationTheoretic Framework for Nonlinear Canonical Correlation Analysis
Canonical Correlation Analysis (CCA) is a linear representation learning...
read it

Learning to Prune: Speeding up Repeated Computations
It is common to encounter situations where one must solve a sequence of ...
read it

Causal Feature Discovery through Strategic Modification
We consider an online regression setting in which individuals adapt to t...
read it

On the Complexity of Minimizing Convex Finite Sums Without Using the Indices of the Individual Functions
Recent advances in randomized incremental methods for minimizing Lsmoot...
read it

Why do deep convolutional networks generalize so poorly to small image transformations?
Deep convolutional network architectures are often assumed to guarantee ...
read it

Equal Opportunity in Online Classification with Partial Feedback
We study an online classification problem with partial feedback in which...
read it

On selfplay computation of equilibrium in poker
We compare performance of the genetic algorithm and the counterfactual r...
read it

On GANs and GMMs
A longstanding problem in machine learning is to find unsupervised metho...
read it

Learning Parities with Neural Networks
In recent years we see a rapidly growing line of research which shows le...
read it

Ballpark Crowdsourcing: The Wisdom of Rough Group Comparisons
Crowdsourcing has become a popular method for collecting labeled trainin...
read it

On evolutionary selection of blackjack strategies
We apply the approach of evolutionary programming to the problem of opti...
read it

Benefits of Depth for LongTerm Memory of Recurrent Networks
The key attribute that drives the unprecedented success of modern Recurr...
read it

SumProductQuotient Networks
We present a novel tractable generative model that extends SumProduct N...
read it

Neuronlevel Selective Context Aggregation for Scene Segmentation
Contextual information provides important cues for disambiguating visual...
read it

Gaussian Lower Bound for the Information Bottleneck Limit
The Information Bottleneck (IB) is a conceptual method for extracting th...
read it

Analysis and Design of Convolutional Networks via Hierarchical Tensor Decompositions
The driving force behind convolutional networks  the most successful de...
read it

Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design
Deep convolutional networks have witnessed unprecedented success in vari...
read it

Optimal Shrinkage of Singular Values Under Random Data Contamination
A low rank matrix X has been contaminated by uniformly distributed noise...
read it

On the Expressive Power of Overlapping Architectures of Deep Learning
Expressive efficiency refers to the relation between two architectures A...
read it

Tractable Generative Convolutional Arithmetic Circuits
Casting neural networks in generative frameworks is a highly soughtafte...
read it

Accelerating Innovation Through Analogy Mining
The availability of large idea repositories (e.g., the U.S. patent datab...
read it

Inductive Bias of Deep Convolutional Networks through Pooling Geometry
Our formal understanding of the inductive bias that drives the success o...
read it

Convolutional Rectifier Networks as Generalized Tensor Decompositions
Convolutional rectifier networks, i.e. convolutional neural networks wit...
read it

Linear Readout of Object Manifolds
Objects are represented in sensory systems by continuous manifolds due t...
read it

On the Expressive Power of Deep Learning: A Tensor Analysis
It has long been conjectured that hypotheses spaces suitable for data th...
read it

Deep SimNets
We present a deep layered architecture that generalizes convolutional ne...
read it

Learning Data Manifolds with a Cutting Plane Method
We consider the problem of classifying data manifolds where each manifol...
read it

An Axiomatic Approach to Routing
Information delivery in a network of agents is a key issue for large, co...
read it

Strategyproof Peer Selection using Randomization, Partitioning, and Apportionment
Peer review, evaluation, and selection is a fundamental aspect of modern...
read it

Covariance Plasticity and Regulated Criticality
We propose that a regulation mechanism based on Hebbian covariance plast...
read it

InformationTheoretic Bounded Rationality
Bounded rationality, that is, decisionmaking and planning under resourc...
read it

A Tight Convex Upper Bound on the Likelihood of a Finite Mixture
The likelihood function of a finite mixture model is a nonconvex functi...
read it

Online Trajectory Segmentation and Summary With Applications to Visualization and Retrieval
Trajectory segmentation is the process of subdividing a trajectory into ...
read it

Ballpark Learning: Estimating Labels from Rough Group Comparisons
We are interested in estimating individual labels given only coarse, agg...
read it

Estimating mutual information in high dimensions via classification error
Multivariate pattern analyses approaches in neuroimaging are fundamental...
read it

How many faces can be recognized? Performance extrapolation for multiclass classification
The difficulty of multiclass classification generally increases with th...
read it

Memory shapes time perception and intertemporal choices
There is a consensus that human and nonhuman subjects experience tempor...
read it

Optimized Linear Imputation
Often in realworld datasets, especially in high dimensional data, some ...
read it

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

LowRank Matrix Recovery from RowandColumn Affine Measurements
We propose and study a rowandcolumn affine measurement scheme for low...
read it

Predicting Personal Traits from Facial Images using Convolutional Neural Networks Augmented with Facial Landmark Information
We consider the task of predicting various traits of a person given an i...
read it

Learning Finegrained Features via a CNN Tree for Largescale Classification
We propose a novel approach to enhance the discriminability of Convoluti...
read it

Efficient coordinatedescent for orthogonal matrices through Givens rotations
Optimizing over the set of orthogonal matrices is a central component in...
read it

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

Typical models: minimizing false beliefs
A knowledge system S describing a part of real world does in general not...
read it

General Deformations of Point Configurations Viewed By a Pinhole Model Camera
This paper is a theoretical study of the following NonRigid Structure f...
read it

Marginal Likelihoods for Distributed Parameter Estimation of Gaussian Graphical Models
We consider distributed estimation of the inverse covariance matrix, als...
read it

Learning Sparse LowThreshold Linear Classifiers
We consider the problem of learning a nonnegative linear classifier wit...
read it
Hebrew University of Jerusalem
The Hebrew University of Jerusalem is Israel's secondoldest university, established in 1918, 30 years before the establishment of the State of Israel.