Search Results for author:
Found 44 papers, 13 papers with code
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications.
Sum-of-Squares Polynomial Flow
Triangular map is a recent construct in probability theory that allows one to transform any source probability density function to any target density function.
Stronger and Faster Wasserstein Adversarial Attacks
While the majority of existing attacks focus on measuring perturbations under the $\ell_p$ metric, Wasserstein distance, which takes geometry in pixel space into account, has long been known to be a suitable metric for measuring image quality and has recently risen as a compelling alternative to the $\ell_p$ metric in adversarial attacks.
Network Comparison with Interpretable Contrastive Network Representation Learning
This analysis task could be greatly assisted by contrastive learning, which is an emerging analysis approach to discover salient patterns in one dataset relative to another.
Federated Learning Meets Multi-objective Optimization
Federated learning has emerged as a promising, massively distributed way to train a joint deep model over large amounts of edge devices while keeping private user data strictly on device.
Density Deconvolution with Normalizing Flows
Density deconvolution is the task of estimating a probability density function given only noise-corrupted samples.
Showing Your Work Doesn't Always Work
In natural language processing, a recently popular line of work explores how to best report the experimental results of neural networks.
Robust Multiple Kernel k-means Clustering using Min-Max Optimization
To address this problem and inspired by recent works in adversarial learning, we propose a multiple kernel clustering method with the min-max framework that aims to be robust to such adversarial perturbation.
Additive Approximations in High Dimensional Nonparametric Regression via the SALSA
Between non-additive models which often have large variance and first order additive models which have large bias, there has been little work to exploit the trade-off in the middle via additive models of intermediate order.
Unsupervised Multilingual Alignment using Wasserstein Barycenter
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data.
Ranked #1 on
Word Alignment
on en-es
Multivariate Triangular Quantile Maps for Novelty Detection
Novelty detection, a fundamental task in machine learning, has drawn a lot of recent attention due to its wide-ranging applications and the rise of neural approaches.
Newton-type Methods for Minimax Optimization
We prove their local convergence at strict local minimax points, which are surrogates of global solutions.
Convergence of Gradient Methods on Bilinear Zero-Sum Games
Min-max formulations have attracted great attention in the ML community due to the rise of deep generative models and adversarial methods, while understanding the dynamics of gradient algorithms for solving such formulations has remained a grand challenge.
Provably noise-robust, regularised $k$-means clustering
We focus on the $k$-means objective and we prove that the regularised version of $k$-means is NP-Hard even for $k=1$.
Convex-constrained Sparse Additive Modeling and Its Extensions
Sparse additive modeling is a class of effective methods for performing high-dimensional nonparametric regression.
Dropout with Expectation-linear Regularization
Algorithmically, we show that our proposed measure of the inference gap can be used to regularize the standard dropout training objective, resulting in an \emph{explicit} control of the gap.
Distributed Machine Learning via Sufficient Factor Broadcasting
Matrix-parametrized models, including multiclass logistic regression and sparse coding, are used in machine learning (ML) applications ranging from computer vision to computational biology.
Distributed Machine Learning via Sufficient Factor Broadcasting
Matrix-parametrized models, including multiclass logistic regression and sparse coding, are used in machine learning (ML) applications ranging from computer vision to computational biology.
Petuum: A New Platform for Distributed Machine Learning on Big Data
What is a systematic way to efficiently apply a wide spectrum of advanced ML programs to industrial scale problems, using Big Models (up to 100s of billions of parameters) on Big Data (up to terabytes or petabytes)?
Generalized Conditional Gradient for Sparse Estimation
Structured sparsity is an important modeling tool that expands the applicability of convex formulations for data analysis, however it also creates significant challenges for efficient algorithm design.
Deep Homogeneous Mixture Models: Representation, Separation, and Approximation
At their core, many unsupervised learning models provide a compact representation of homogeneous density mixtures, but their similarities and differences are not always clearly understood.
Bregman Divergence for Stochastic Variance Reduction: Saddle-Point and Adversarial Prediction
Adversarial machines, where a learner competes against an adversary, have regained much recent interest in machine learning.
Convex Two-Layer Modeling with Latent Structure
Unsupervised learning of structured predictors has been a long standing pursuit in machine learning.
Polar Operators for Structured Sparse Estimation
Structured sparse estimation has become an important technique in many areas of data analysis.
On Decomposing the Proximal Map
The proximal map is the key step in gradient-type algorithms, which have become prevalent in large-scale high-dimensional problems.
Better Approximation and Faster Algorithm Using the Proximal Average
It is a common practice to approximate complicated'' functions with more friendly ones.
Convex Multi-view Subspace Learning
Subspace learning seeks a low dimensional representation of data that enables accurate reconstruction.
A Polynomial-time Form of Robust Regression
Despite the variety of robust regression methods that have been developed, current regression formulations are either NP-hard, or allow unbounded response to even a single leverage point.
Accelerated Training for Matrix-norm Regularization: A Boosting Approach
Sparse learning models typically combine a smooth loss with a nonsmooth penalty, such as trace norm.
Relaxed Clipping: A Global Training Method for Robust Regression and Classification
We present a generic procedure that can be applied to standard loss functions and demonstrate improved robustness in regression and classification problems.
A General Projection Property for Distribution Families
We prove that linear projections between distribution families with fixed first and second moments are surjective, regardless of dimension.
Learning Latent Space Models with Angular Constraints
The large model capacity of latent space models (LSMs) enables them to achieve great performance on various applications, but meanwhile renders LSMs to be prone to overfitting.
Inductive Two-Layer Modeling with Parametric Bregman Transfer
Latent prediction models, exemplified by multi-layer networks, employ hidden variables that automate abstract feature discovery.
They Are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers
Complex event detection on unconstrained Internet videos has seen much progress in recent years.
Closed-Form Training of Mahalanobis Distance for Supervised Clustering
Clustering is the task of grouping a set of objects so that objects in the same cluster are more similar to each other than to those in other clusters.
Efficient Multiple Instance Metric Learning Using Weakly Supervised Data
Classic approaches alternate the optimization over the learned metric and the assignment of similar instances.
Distributional Reinforcement Learning for Efficient Exploration
In distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties.
Tails of Lipschitz Triangular Flows
We investigate the ability of popular flow based methods to capture tail-properties of a target density by studying the increasing triangular maps used in these flow methods acting on a tractable source density.
Understanding Adversarial Robustness: The Trade-off between Minimum and Average Margin
Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models.
What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons
Memory neurons of long short-term memory (LSTM) networks encode and process information in powerful yet mysterious ways.
Exploiting Token and Path-based Representations of Code for Identifying Security-Relevant Commits
Public vulnerability databases such as CVE and NVD account for only 60% of security vulnerabilities present in open-source projects, and are known to suffer from inconsistent quality.
Optimality and Stability in Non-Convex Smooth Games
Convergence to a saddle point for convex-concave functions has been studied for decades, while recent years has seen a surge of interest in non-convex (zero-sum) smooth games, motivated by their recent wide applications.
A Positivstellensatz for Conditional SAGE Signomials
Recently, the conditional SAGE certificate has been proposed as a sufficient condition for signomial positivity over a convex set.
Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space
Invariance (defined in a general sense) has been one of the most effective priors for representation learning.
