Search Results for author:
Found 7 papers, 1 papers with code
Optimal Sample Complexity of Contrastive Learning
Contrastive learning is a highly successful technique for learning representations of data from labeled tuples, specifying the distance relations within the tuple.
Tree Learning: Optimal Algorithms and Sample Complexity
Consider a collection of data tuples labeled according to their hierarchical structure.
HOUDINI: Escaping from Moderately Constrained Saddles
We give the first polynomial time algorithms for escaping from high-dimensional saddle points under a moderate number of constraints.
Escaping Saddle Points with Compressed SGD
Gradient compression methods can be used to alleviate this problem, and a recent line of work shows that SGD augmented with gradient compression converges to an $\varepsilon$-first-order stationary point.
Objective-Based Hierarchical Clustering of Deep Embedding Vectors
In order to address the challenge of scaling up hierarchical clustering to such large datasets we propose a new practical hierarchical clustering algorithm B++&C.
"Bring Your Own Greedy"+Max: Near-Optimal $1/2$-Approximations for Submodular Knapsack
Our analysis is based on a new set of first-order linear differential inequalities and their robust approximate versions.
Adversarially Robust Submodular Maximization under Knapsack Constraints
We propose the first adversarially robust algorithm for monotone submodular maximization under single and multiple knapsack constraints with scalable implementations in distributed and streaming settings.
