
FrankWolfe with a Nearest Extreme Point Oracle
We consider variants of the classical FrankWolfe algorithm for constrai...
read it

On the Efficient Implementation of the Matrix Exponentiated Gradient Algorithm for LowRank Matrix Optimization
Convex optimization over the spectrahedron, i.e., the set of all real n×...
read it

Revisiting Projectionfree Online Learning: the Strongly Convex Case
Projectionfree optimization algorithms, which are mostly based on the c...
read it

Revisiting FrankWolfe for Polytopes: Strict Complementary and Sparsity
In recent years it was proved that simple modifications of the classical...
read it

On the Convergence of Stochastic Gradient Descent with LowRank Projections for Convex LowRank Matrix Problems
We revisit the use of Stochastic Gradient Descent (SGD) for solving conv...
read it

Linear Convergence of FrankWolfe for RankOne Matrix Recovery Without Strong Convexity
We consider convex optimization problems which are widely used as convex...
read it

Improved Regret Bounds for Projectionfree Bandit Convex Optimization
We revisit the challenge of designing online algorithms for the bandit c...
read it

On the Convergence of ProjectedGradient Methods with LowRank Projections for Smooth Convex Minimization over TraceNorm Balls and Related Problems
Smooth convex minimization over the unit tracenorm ball is an important...
read it

On the Regret Minimization of Nonconvex Online Gradient Ascent for Online PCA
Nonconvex optimization with global convergence guarantees is gaining si...
read it

Fast Stochastic Algorithms for Lowrank and Nonsmooth Matrix Problems
Composite convex optimization problems which include both a nonsmooth te...
read it

Learning of Optimal Forecast Aggregation in Partial Evidence Environments
We consider the forecast aggregation problem in repeated settings, where...
read it

Fast Generalized Conditional Gradient Method with Applications to Matrix Recovery Problems
Motivated by matrix recovery problems such as Robust Principal Component...
read it

Fast Rates for Online Gradient Descent Without Strong Convexity via Hoffman's Bound
Hoffman's classical result gives a bound on the distance of a point from...
read it

Efficient coordinatewise leading eigenvector computation
We develop and analyze efficient "coordinatewise" methods for finding t...
read it

Stochastic Canonical Correlation Analysis
We tightly analyze the sample complexity of CCA, provide a learning algo...
read it

A Linearly Convergent Conditional Gradient Algorithm with Applications to Online and Stochastic Optimization
Linear optimization is many times algorithmically simpler than nonlinea...
read it
Dan Garber
is this you? claim profile