
A Local Convergence Theory for Mildly OverParameterized TwoLayer Neural Network
While overparameterization is widely believed to be crucial for the suc...
read it

Beyond Lazy Training for Overparameterized Tensor Decomposition
Overparametrization is an important technique in training neural networ...
read it

Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks
Hessian captures important properties of the deep neural network loss la...
read it

Efficient sampling from the Bingham distribution
We give a algorithm for exact sampling from the Bingham distribution p(x...
read it

Guarantees for Tuning the Step Size using a LearningtoLearn Approach
Learningtolearn (using optimization algorithms to learn a new optimize...
read it

Optimization Landscape of Tucker Decomposition
Tucker decomposition is a popular technique for many data analysis and m...
read it

Extracting Latent State Representations with Linear Dynamics from Rich Observations
Recently, many reinforcement learning techniques were shown to have prov...
read it

EnergyAware DNN Graph Optimization
Unlike existing work in deep neural network (DNN) graphs optimization fo...
read it

HighDimensional Robust Mean Estimation via Gradient Descent
We study the problem of highdimensional robust mean estimation in the p...
read it

Spectral Learning on Matrices and Tensors
Spectral methods have been the mainstay in several domains such as machi...
read it

Estimating Normalizing Constants for LogConcave Distributions: Algorithms and Lower Bounds
Estimating the normalizing constant of an unnormalized probability distr...
read it

Mildly Overparametrized Neural Nets can Memorize Training Data Efficiently
It has been observed zhang2016understanding that deep neural networks ca...
read it

Explaining Landscape Connectivity of Lowcost Solutions for Multilayer Nets
Mode connectivity is a surprising phenomenon in the loss landscape of de...
read it

Faster Algorithms for HighDimensional Robust Covariance Estimation
We study the problem of estimating the covariance matrix of a highdimen...
read it

Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization
Variance reduction techniques like SVRG provide simple and fast algorith...
read it

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure
There is a stark disparity between the step size schedules used in pract...
read it

Stochastic Gradient Descent Escapes Saddle Points Efficiently
This paper considers the perturbed stochastic gradient descent algorithm...
read it

A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm
In this note, we derive concentration inequalities for random vectors wi...
read it

Understanding Composition of Word Embeddings via Tensor Decomposition
Word embedding is a powerful tool in natural language processing. In thi...
read it

Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition
A key task in Bayesian machine learning is sampling from distributions t...
read it

HighDimensional Robust Mean Estimation in NearlyLinear Time
We study the fundamental problem of highdimensional mean estimation in ...
read it

Learning Twolayer Neural Networks with Symmetric Inputs
We give a new algorithm for learning a twolayer neural network under a ...
read it

NonConvex Matrix Completion Against a SemiRandom Adversary
Matrix completion is a wellstudied problem with many machine learning a...
read it

Minimizing Nonconvex Population Risk from Rough Empirical Risk
Population riskthe expectation of the loss over the sampling mechanis...
read it

Stronger generalization bounds for deep nets via a compression approach
Deep nets generalize well despite having more parameters than the number...
read it

Global Convergence of Policy Gradient Methods for Linearized Control Problems
Direct policy gradient methods for reinforcement learning and continuous...
read it

Learning Onehiddenlayer Neural Networks with Landscape Design
We consider the problem of learning a onehiddenlayer neural network: w...
read it

Beyond Logconcavity: Provable Guarantees for Sampling Multimodal Distributions using Simulated Tempering Langevin Monte Carlo
A key task in Bayesian statistics is sampling from distributions that ar...
read it

On the Optimization Landscape of Tensor Decompositions
Nonconvex optimization with local search heuristics has been widely use...
read it

No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis
In this paper we develop a new framework that captures the common landsc...
read it

How to Escape Saddle Points Efficiently
This paper shows that a perturbed form of gradient descent converges to ...
read it

Generalization and Equilibrium in Generative Adversarial Nets (GANs)
We show that training of generative adversarial network (GAN) may not ha...
read it

Provable learning of Noisyor Networks
Many machine learning applications use latent variable models to explain...
read it

Homotopy Analysis for Tensor PCA
Developing efficient and guaranteed nonconvex algorithms has been an imp...
read it

DynIMS: A Dynamic Memory Controller for Inmemory Storage on HPC Systems
In order to boost the performance of dataintensive computing on HPC sys...
read it

Provable Algorithms for Inference in Topic Models
Recently, there has been considerable progress on designing algorithms w...
read it

Matrix Completion has No Spurious Local Minimum
Matrix completion is a basic machine learning problem that has wide appl...
read it

Efficient Algorithms for Largescale Generalized Eigenvector Computation and Canonical Correlation Analysis
This paper considers the problem of canonicalcorrelation analysis (CCA)...
read it

Efficient approaches for escaping higher order saddle points in nonconvex optimization
Local search heuristics for nonconvex optimizations are popular in appl...
read it

Intersecting Faces: Nonnegative Matrix Factorization With New Guarantees
Nonnegative matrix factorization (NMF) is a natural model of admixture ...
read it

Unregularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization
We develop a family of accelerated stochastic algorithms that minimize s...
read it

Decomposing Overcomplete 3rd Order Tensors using SumofSquares Algorithms
Tensor rank and lowrank tensor decompositions have many applications in...
read it

Escaping From Saddle Points  Online Stochastic Gradient for Tensor Decomposition
We analyze stochastic gradient descent for optimizing nonconvex functio...
read it

Simple, Efficient, and Neural Algorithms for Sparse Coding
Sparse coding is a basic task in many fields including signal processing...
read it

Competing with the Empirical Risk Minimizer in a Single Pass
In many estimation problems, e.g. linear and logistic regression, we wis...
read it

Analyzing Tensor Power Method Dynamics in Overcomplete Regime
We present a novel analysis of the dynamics of tensor power iterations i...
read it

Sample Complexity Analysis for Learning Overcomplete Latent Variable Models through Tensor Methods
We provide guarantees for learning latent variable models emphasizing on...
read it

Guaranteed NonOrthogonal Tensor Decomposition via Alternating Rank1 Updates
In this paper, we provide local and global convergence guarantees for re...
read it

More Algorithms for Provable Dictionary Learning
In dictionary learning, also known as sparse coding, the algorithm is gi...
read it

New Algorithms for Learning Incoherent and Overcomplete Dictionaries
In sparse recovery we are given a matrix A (the dictionary) and a vector...
read it
Rong Ge
is this you? claim profile
Assistant Professor at the Computer Science Department of Duke University.