Neural networks can be significantly compressed by pruning, leading to s...
In this work, we study optimization problems of the form min_x max_y f(x...
Mixed Integer Programming (MIP) is NP-hard, and yet modern solvers often...
We propose a globally-accelerated, first-order method for the optimizati...
Mixed-integer nonlinear optimization is a broad class of problems that
f...
The approximate vanishing ideal of a set of points X = {𝐱_1,
…, 𝐱_m}⊆ [0...
We present a new theoretical framework for making black box classifiers ...
Many existing Neural Network pruning approaches either rely on retrainin...
For a matrix W ∈ℤ^m × n, m ≤ n, and a convex
function g: ℝ^m →ℝ, we are ...
Combinatorial optimization is a well-established area in operations rese...
One of the goals of Explainable AI (XAI) is to determine which input
com...
Network pruning is a widely used technique for effectively compressing D...
We study the effects of constrained optimization formulations and Frank-...
Several learning problems involve solving min-max problems, e.g., empiri...
Generalized self-concordance is a key property present in the objective
...
Primal heuristics play a crucial role in exact solvers for Mixed Integer...
Linear bandit algorithms yield 𝒪̃(n√(T)) pseudo-regret
bounds on compact...
Projection-free conditional gradient (CG) methods are the algorithms of
...
We review various characterizations of uniform convexity and smoothness ...
We revisit the concept of "adversary" in online learning, motivated by
s...
The Frank-Wolfe algorithm is a method for constrained optimization that
...
Governing equations are essential to the study of nonlinear dynamics, of...
This paper studies the empirical efficacy and benefits of using
projecti...
The complexity in large-scale optimization can lie in both handling the
...
Fast domain propagation of linear constraints has become a crucial compo...
Descent directions such as movement towards Frank-Wolfe vertices, away s...
The Frank-Wolfe algorithm has become a popular first-order optimization
...
Constrained second-order convex optimization algorithms are the method o...
Recently non-convex optimization approaches for solving machine learning...
Submodular maximization has been widely studied over the past decades, m...
The approximate Carathéodory theorem states that given a polytope
P, eac...
Conditional gradient methods form a class of projection-free first-order...
Matching pursuit algorithms are an important class of algorithms in sign...
In this paper, we demonstrate how to learn the objective function of a
d...
Deep Learning has received significant attention due to its impressive
p...
In this work, we consider robust submodular maximization with matroid
co...
Sparse structures are frequently sought when pursuing tractability in
op...
We present a blended conditional gradient approach for minimizing a smoo...
We study reinforcement learning under model misspecification, where we d...
In this work we introduce a conditional accelerated lazy stochastic grad...
We study the value of information in sequential compressed sensing by
ch...
We characterize the performance of sequential information guided sensing...
We present an information-theoretic framework for sequential adaptive
co...