papers

Publications (21)

cs.LG2019

Convolutional Bipartite Attractor Networks

Michael Iuzzolino, Yoram Singer, Michael C. Mozer

In human perception and cognition, a fundamental operation that brains perform is interpretation: constructing coherent neural states from noisy, incomplete, and intrinsically ambi…

cs.LG2017

Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity

Amit Daniely, Roy Frostig, Yoram Singer

We develop a general duality between neural networks and compositional kernels, striving towards a better understanding of deep learning. We show that initial representations gener…

cs.LG2013

The Maximum Entropy Relaxation Path

Moshe Dubiner, Matan Gavish, Yoram Singer

The relaxed maximum entropy problem is concerned with finding a probability distribution on a finite set that minimizes the relative entropy to a given prior distribution, while sa…

cs.LG2013

Update Rules for Parameter Estimation in Bayesian Networks

Eric Bauer, Daphne Koller, Yoram Singer

This paper re-examines the problem of parameter estimation in Bayesian networks with missing values and hidden variables from the perspective of recent work in on-line learning [Ki…

cmp-lg1996

Beyond Word N-Grams

Fernando C. N. Pereira, Yoram Singer, Naftali Tishby

We describe, analyze, and evaluate experimentally a new probabilistic model for word-sequence prediction in natural language based on prediction suffix trees (PSTs). By using effic…

cs.LG2016

Sketching and Neural Networks

Amit Daniely, Nevena Lazic, Yoram Singer +1

High-dimensional sparse data present computational and statistical challenges for supervised learning. We propose compact linear sketches for reducing the dimensionality of the inp…

cs.CV2013

Using Web Co-occurrence Statistics for Improving Image Categorization

Samy Bengio, Jeff Dean, Dumitru Erhan +5

Object recognition and localization are important tasks in computer vision. The focus of this work is the incorporation of contextual information in order to improve object recogni…

cs.LG2020

Proximity Preserving Binary Code using Signed Graph-Cut

Inbal Lav, Shai Avidan, Yoram Singer +1

We introduce a binary embedding framework, called Proximity Preserving Code (PPC), which learns similarity and dissimilarity between data points to create a compact and affinity-pr…

stat.ML2022

Are All Layers Created Equal?

Chiyuan Zhang, Samy Bengio, Yoram Singer

Understanding deep neural networks is a major research objective with notable experimental and theoretical attention in recent years. The practical success of excessively large net…

cs.LG2016

Train faster, generalize better: Stability of stochastic gradient descent

Moritz Hardt, Benjamin Recht, Yoram Singer

We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is al…

cs.LG2017

A Unified Approach to Adaptive Regularization in Online and Stochastic Optimization

Vineet Gupta, Tomer Koren, Yoram Singer

We describe a framework for deriving and analyzing online optimization algorithms that incorporate adaptive, data-dependent regularization, also termed preconditioning. Such algori…

cs.LG2013

Matrix Approximation under Local Low-Rank Assumption

Joonseok Lee, Seungyeon Kim, Guy Lebanon +1

Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumpti…

cs.LG2017

Random Features for Compositional Kernels

Amit Daniely, Roy Frostig, Vineet Gupta +1

We describe and analyze a simple random feature scheme (RFS) from prescribed compositional kernels. The compositional kernels we use are inspired by the structure of convolutional…

cs.DS2018

The Well Tempered Lasso

Yuanzhi Li, Yoram Singer

We study the complexity of the entire regularization path for least squares regression with 1-norm penalty, known as the Lasso. Every regression parameter in the Lasso changes line…

q-fin.PM2013

Switching Portfolios

Yoram Singer

A constant rebalanced portfolio is an asset allocation algorithm which keeps the same distribution of wealth among a set of assets along a period of time. Recently, there has been…

cs.LG2018

Shampoo: Preconditioned Stochastic Tensor Optimization

Vineet Gupta, Tomer Koren, Yoram Singer

Preconditioned gradient methods are among the most general and powerful tools in optimization. However, preconditioning requires storing and manipulating prohibitively large matric…

cs.LG2019

Memory-Efficient Adaptive Optimization

Rohan Anil, Vineet Gupta, Tomer Koren +1

Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these meth…

stat.ML2020

Identity Crisis: Memorization and Generalization under Extreme Overparameterization

Chiyuan Zhang, Samy Bengio, Moritz Hardt +2

We study the interplay between memorization and generalization of overparameterized networks in the extreme case of a single training example and an identity-mapping task. We exami…

cs.LG2014

Zero-Shot Learning by Convex Combination of Semantic Embeddings

Mohammad Norouzi, Tomas Mikolov, Samy Bengio +5

Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image…

cs.LG2021

Scalable Second Order Optimization for Deep Learning

Rohan Anil, Vineet Gupta, Tomer Koren +2

Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimizatio…

cs.LG2019

Exponentiated Gradient Meets Gradient Descent

Udaya Ghai, Elad Hazan, Yoram Singer

The (stochastic) gradient descent and the multiplicative update method are probably the most popular algorithms in machine learning. We introduce and study a new regularization whi…