
Classification vs regression in overparameterized regimes: Does the loss function matter?
We compare classification and regression tasks in the overparameterized ...
read it

Correcting the bias in least squares regression with volumerescaled sampling
Consider linear regression where the examples are generated by an unknow...
read it

Weakly Supervised Attention Networks for FineGrained Opinion Mining and Public Health
In many review classification applications, a finegrained analysis of t...
read it

A New Framework for Query Efficient Active Imitation Learning
We seek to align agent policy with human expert behavior in a reinforcem...
read it

Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate
Many modern machine learning models are trained to achieve zero or near...
read it

Reconciling modern machine learning and the biasvariance tradeoff
The question of generalization in machine learninghow algorithms are ...
read it

Two models of double descent for weak features
The "double descent" risk curve was recently proposed to qualitatively d...
read it

How many variables should be entered in a principal component regression equation?
We study least squares linear regression over N uncorrelated Gaussian fe...
read it

Leveraging Just a Few Keywords for FineGrained Aspect Detection Through Weakly Supervised CoTraining
Usergenerated reviews can be decomposed into finegrained segments (e.g...
read it

Contrastive estimation reveals topic posterior information to linear models
Contrastive learning is an approach to representation learning that util...
read it

Diameterbased Interactive Structure Search
In this work, we introduce interactive structure search, a generic frame...
read it

Unbiased estimators for random design regression
In linear regression we wish to estimate the optimum linear least square...
read it

Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform
Companies increasingly expose machine learning (ML) models trained over ...
read it

Benefits of overparameterization with EM
Expectation Maximization (EM) is among the most popular algorithms for m...
read it

A cryptographic approach to black box adversarial machine learning
We propose an ensemble technique for converting any classifier into a co...
read it

A gradual, semidiscrete approach to generative network training via explicit wasserstein minimization
This paper provides a simple procedure to fit generative networks to tar...
read it

Time Series Compression Based on Adaptive Piecewise Recurrent Autoencoder
Time series account for a large proportion of the data stored in financi...
read it

Time Series Forecasting Based on Augmented Long ShortTerm Memory
In this paper, we use recurrent autoencoder model to predict the time se...
read it

Mixing time estimation in reversible Markov chains from a single sample path
The spectral gap γ of a finite, ergodic, and reversible Markov chain is ...
read it

Anomaly Detection on Graph Time Series
In this paper, we use variational recurrent neural network to investigat...
read it

Parameter identification in Markov chain choice models
This work studies the parameter identification problem for the Markov ch...
read it

Linear regression without correspondence
This article considers algorithmic and statistical aspects of linear reg...
read it

Global analysis of Expectation Maximization for mixtures of two Gaussians
Expectation Maximization (EM) is among the most popular algorithms for e...
read it

Search Improves Label for Active Learning
We investigate active learning with access to two distinct oracles: Labe...
read it

Scalable Nonlinear Learning with Adaptive Polynomial Expansions
Can we effectively learn a nonlinear representation in time comparable t...
read it

Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
We present a new algorithm for the contextual bandit learning problem, w...
read it

When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity
Overcomplete latent representations have been very popular for unsupervi...
read it

Loss minimization and parameter estimation with heavy tails
This work studies applications and generalizations of a simple estimatio...
read it

A Tensor Approach to Learning Mixed Membership Community Models
Community detection is the task of detecting hidden communities from obs...
read it

Learning Sparse LowThreshold Linear Classifiers
We consider the problem of learning a nonnegative linear classifier wit...
read it

Analysis of a randomized approximation scheme for matrix multiplication
This note gives a simple analysis of a randomized approximation scheme f...
read it

Tensor decompositions for learning latent variable models
This work considers a computationally and statistically efficient parame...
read it

Learning Topic Models and Latent Bayesian Networks Under Expansion Constraints
Unsupervised estimation of latent variable models is a fundamental probl...
read it

Convergence Rates for Differentially Private Statistical Estimation
Differential privacy is a cryptographicallymotivated definition of priv...
read it

A concentration theorem for projections
X in R^D has mean zero and finite second moments. We show that there is ...
read it

Learning mixtures of spherical Gaussians: moment methods and spectral decompositions
This work provides a computationally efficient and statistically consist...
read it

A Spectral Algorithm for Latent Dirichlet Allocation
The problem of topic modeling can be seen as a generalization of the clu...
read it

An Online Learningbased Framework for Tracking
We study the tracking problem, namely, estimating the hidden state of an...
read it

A Method of Moments for Mixture Models and Hidden Markov Models
Mixture models are a fundamental tool in applied statistics and machine ...
read it

Spectral Methods for Learning Multivariate Latent Tree Structure
This work considers the problem of learning the structure of multivariat...
read it

Efficient Optimal Learning for Contextual Bandits
We address the problem of learning in an online setting where the learne...
read it

Random design analysis of ridge regression
This work gives a simultaneous analysis of both the ordinary least squar...
read it

Dimensionfree tail inequalities for sums of random matrices
We derive exponential tail inequalities for sums of random matrices with...
read it

Robust Matrix Decomposition with Outliers
Suppose a given observation matrix can be decomposed as the sum of a low...
read it

Tracking using explanationbased modeling
We study the tracking problem, namely, estimating the hidden state of an...
read it

Kernel Approximation Methods for Speech Recognition
We study largescale kernel methods for acoustic modeling in speech reco...
read it

NonGaussian information from weak lensing data via deep learning
Weak lensing maps contain information beyond twopoint statistics on sma...
read it

Tail bounds for volume sampled linear regression
The n × d design matrix in a linear regression problem is given, but the...
read it

On the Connection between Differential Privacy and Adversarial Robustness in Machine Learning
Adversarial examples in machine learning has been a topic of intense res...
read it

Successive RankOne Approximations for Nearly Orthogonally Decomposable Symmetric Tensors
Many idealized problems in signal processing, machine learning and stati...
read it