User profiles for Pratik Jain
Prateek JainGoogle Research India Verified email at google.com Cited by 19373 |
Information-theoretic metric learning
In this paper, we present an information-theoretic approach to learning a Mahalanobis distance
function. We formulate the problem as that of minimizing the differential relative entropy …
function. We formulate the problem as that of minimizing the differential relative entropy …
Low-rank matrix completion using alternating minimization
Alternating minimization represents a widely applicable and empirically successful approach
for finding low-rank matrices that best fit the given data. For example, for the problem of low-…
for finding low-rank matrices that best fit the given data. For example, for the problem of low-…
Pennylane: Automatic differentiation of hybrid quantum-classical computations
PennyLane is a Python 3 software framework for differentiable programming of quantum
computers. The library provides a unified architecture for near-term quantum computing devices…
computers. The library provides a unified architecture for near-term quantum computing devices…
Phase retrieval using alternating minimization
Phase retrieval problems involve solving linear equations, but with missing sign (or phase,
for complex numbers) information. Over the last two decades, a popular generic empirical …
for complex numbers) information. Over the last two decades, a popular generic empirical …
Guaranteed rank minimization via singular value projection
Minimizing the rank of a matrix subject to affine constraints is a fundamental problem with
many important applications in machine learning and statistics. In this paper we propose a …
many important applications in machine learning and statistics. In this paper we propose a …
Large-scale multi-label learning with missing labels
The multi-label classification problem has generated significant interest in recent years.
However, existing approaches do not adequately address two key challenges:(a) scaling up to …
However, existing approaches do not adequately address two key challenges:(a) scaling up to …
Non-convex optimization for machine learning
P Jain, P Kar - Foundations and Trends® in Machine …, 2017 - nowpublishers.com
A vast majority of machine learning algorithms train their models and perform inference by
solving optimization problems. In order to capture the learning and prediction problems …
solving optimization problems. In order to capture the learning and prediction problems …
Sparse local embeddings for extreme multi-label classification
The objective in extreme multi-label learning is to train a classifier that can automatically tag
a novel data point with the most relevant subset of labels from an extremely large label set. …
a novel data point with the most relevant subset of labels from an extremely large label set. …
The pitfalls of simplicity bias in neural networks
Several works have proposed Simplicity Bias (SB)---the tendency of standard training
procedures such as Stochastic Gradient Descent (SGD) to find simple models---to justify why …
procedures such as Stochastic Gradient Descent (SGD) to find simple models---to justify why …
On the insufficiency of existing momentum schemes for stochastic optimization
R Kidambi, P Netrapalli, P Jain… - 2018 Information Theory …, 2018 - ieeexplore.ieee.org
Momentum based stochastic gradient methods such as heavy ball (HB) and Nesterov's
accelerated gradient descent (NAG) method are widely used in practice for training deep …
accelerated gradient descent (NAG) method are widely used in practice for training deep …