
Adaptive Newton Sketch: Lineartime Optimization with Quadratic Convergence and Effective Hessian Dimensionality
We propose a randomized algorithm with quadratic convergence rate for co...
read it

Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
Neural networks (NNs) have been extremely successful across many tasks i...
read it

Fast Convex Quadratic Optimization Solvers with Adaptive Sketchingbased Preconditioners
We consider leastsquares problems with quadratic regularization and pro...
read it

Distributed Learning and Democratic Embeddings: PolynomialTime Source Coding Schemes Can Achieve Minimax Lower Bounds for Distributed Gradient Descent under Communication Cons
In this work, we consider the distributed optimization setting where inf...
read it

Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization
Batch Normalization (BN) is a commonly used technique to accelerate and ...
read it

Neural Spectrahedra and Semidefinite Lifts: Global Convex Optimization of Polynomial Activation Neural Networks in Fully PolynomialTime
The training of twolayer neural networks with nonlinear activation func...
read it

Vectoroutput ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomialtime Algorithms
We describe the convex semiinfinite dual of the twolayer vectoroutput...
read it

Adaptive and Oblivious Randomized Subspace Methods for HighDimensional Optimization: Sharp Analysis and Lower Bounds
We propose novel randomized optimization methods for highdimensional co...
read it

Convex Regularization Behind Neural Reconstruction
Neural networks have shown tremendous potential for reconstructing high...
read it

Approximate Weighted CR Coded Matrix Multiplication
One of the most common, but at the same time expensive operations in lin...
read it

Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization
In distributed second order optimization, a standard strategy is to aver...
read it

Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two and ThreeLayer Networks in Polynomial Time
We study training of Convolutional Neural Networks (CNNs) with ReLU acti...
read it

Lower Bounds and a NearOptimal Shrinkage Estimator for Least Squares using Random Projections
In this work, we consider the deterministic optimization using random pr...
read it

All Local Minima are Global for TwoLayer ReLU Neural Networks: The Hidden Convex Optimization Landscape
We are interested in twolayer ReLU neural networks from an optimization...
read it

Effective Dimension Adaptive Sketching Methods for Faster Regularized LeastSquares Optimization
We propose a new randomized algorithm for solving L2regularized leasts...
read it

Global Multiclass Classification from Heterogeneous Local Models
Multiclass classification problems are most often solved by either train...
read it

Straggler Robust Distributed Matrix Inverse Approximation
A cumbersome operation in numerical analysis and linear algebra, optimiz...
read it

Convex Geometry and Duality of Overparameterized Neural Networks
We develop a convex analytic framework for ReLU neural networks which el...
read it

Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory
Batch Normalization (BatchNorm) is commonly used in Convolutional Neural...
read it

Neural Networks are Convex Regularizers: Exact Polynomialtime Convex Optimization Formulations for TwoLayer Networks
We develop exact representations of two layer neural networks with recti...
read it

Convex Duality of Deep Neural Networks
We study regularized deep neural networks and introduce an analytic fram...
read it

Optimal Randomized FirstOrder Methods for LeastSquares Problems
We provide an exact analysis of a class of randomized algorithms for sol...
read it

Distributed Averaging Methods for Randomized Second Order Optimization
We consider distributed optimization problems where forming the Hessian ...
read it

Distributed Sketching Methods for Privacy Preserving Regression
In this work, we study distributed sketching methods for large scale reg...
read it

Global Convergence of Frank Wolfe on One Hidden Layer Networks
We derive global convergence bounds for the Frank Wolfe algorithm when t...
read it

Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods
We provide an exact analysis of the limiting spectrum of matrices random...
read it

Weighted Gradient Coding with Leverage Score Sampling
A major hurdle in machine learning is scalability to massive datasets. A...
read it

Regularized Momentum Iterative Hessian Sketch for Large Scale Linear System of Equations
In this article, Momentum Iterative Hessian Sketch (MIHS) techniques, a...
read it

Faster Least Squares Optimization
We investigate randomized methods for solving overdetermined linear leas...
read it

Distributed BlackBox Optimization via Error Correcting Codes
We introduce a novel distributed derivativefree optimization framework ...
read it

HighDimensional Optimization in Adaptive Random Subspaces
We propose a new randomized optimization method for highdimensional pro...
read it

Polar Coded Distributed Matrix Multiplication
We propose a polar coding mechanism for distributed matrix multiplicatio...
read it

Convex Relaxations of Convolutional Neural Nets
We propose convex relaxations for convolutional neural nets with one hid...
read it

Newton Sketch: A Lineartime Optimization Algorithm with LinearQuadratic Convergence
We propose a randomized secondorder method for optimization known as th...
read it

Randomized sketches for kernels: Fast and optimal nonparametric regression
Kernel ridge regression (KRR) is a standard method for performing nonpa...
read it

Iterative Hessian sketch: Fast and accurate solution approximation for constrained leastsquares
We study randomized sketching methods for approximately solving leastsq...
read it

Randomized Sketches of Convex Programs with Sharp Guarantees
Random projection (RP) is a classical technique for reducing storage and...
read it
Mert Pilanci
verfied profile