Search Results for author:
Found 12 papers, 6 papers with code
Accelerated Parameter-Free Stochastic Optimization
We propose a method that achieves near-optimal rates for smooth stochastic convex optimization and requires essentially no prior knowledge of problem parameters.
The Price of Adaptivity in Stochastic Convex Optimization
We prove impossibility results for adaptivity in non-smooth stochastic convex optimization.
Datasets and Benchmarks for Nanophotonic Structure and Parametric Design Simulations
To design and understand these nanophotonic structures, electrodynamic simulations are essential.
DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
Empirically, we consider a broad range of vision and language transfer learning tasks, and show that DoG's performance is close to that of SGD with tuned learning rate.
Optimal Diagonal Preconditioning
Moreover, our implementation of customized solvers, combined with a random row/column sampling step, can find near-optimal diagonal preconditioners for matrices up to size 200, 000 in reasonable time, demonstrating their practical appeal.
Making SGD Parameter-Free
We develop an algorithm for parameter-free stochastic convex optimization (SCO) whose rate of convergence is only a double-logarithmic factor larger than the optimal rate for the corresponding known-parameter setting.
Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices
We present an extension of the conditional gradient method to problems whose feasible sets are convex cones.
An efficient nonconvex reformulation of stagewise convex optimization problems
We establish theoretical properties of the nonconvex formulation, showing that it is (almost) free of spurious local minima and has the same global optimum as the convex problem.
A generic adaptive restart scheme with applications to saddle point algorithms
We provide a simple and generic adaptive restart scheme for convex optimization that is able to achieve worst-case bounds matching (up to constant multiplicative factors) optimal restart schemes that require knowledge of problem specific constants.
Optimization and Control
Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond
This function class, which we call the class of smooth quasar-convex functions, is parameterized by a constant $\gamma \in (0, 1]$, where $\gamma = 1$ encompasses the classes of smooth convex and star-convex functions, and smaller values of $\gamma$ indicate that the function can be "more nonconvex."
“Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions
We develop and analyze a variant of Nesterov’s accelerated gradient descent (AGD) for minimization of smooth non-convex functions.
On the behavior of Lagrange multipliers in convex and non-convex infeasible interior point methods
Alternatively, in the convex case, if the primal feasibility is reduced too fast and the set of Lagrange multipliers is unbounded, then the Lagrange multiplier sequence generated will be unbounded.
Optimization and Control
