Search Results for author:
Found 12 papers, 5 papers with code
PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
This work studies algorithms for learning from aggregate responses.
Greedy PIG: Adaptive Integrated Gradients
We demonstrate the success of Greedy PIG on a wide variety of tasks, including image feature attribution, graph compression/explanation, and post-hoc feature selection on tabular data.
Pipeline Parallelism for DNN Inference with Practical Performance Guarantees
We optimize pipeline parallelism for deep neural network (DNN) inference by partitioning model graphs into $k$ stages and minimizing the running time of the bottleneck stage, including communication.
Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems
Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems.
Learning Rate Schedules in the Presence of Distribution Shift
We design learning rate schedules that minimize regret for SGD-based online learning in the presence of a changing data distribution.
Approximately Optimal Core Shapes for Tensor Decompositions
This work studies the combinatorial optimization problem of finding an optimal core tensor shape, also called multilinear rank, for a size-constrained Tucker decomposition.
Sequential Attention for Feature Selection
Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a budget constraint.
Subquadratic Kronecker Regression with Applications to Tensor Decomposition
By extending our approach to block-design matrices where one block is a Kronecker product, we also achieve subquadratic-time algorithms for (1) Kronecker ridge regression and (2) updating the factor matrices of a Tucker decomposition in ALS, which is not a pure Kronecker regression problem, thereby improving the running time of all steps of Tucker ALS.
Fast Low-Rank Tensor Decomposition by Ridge Leverage Score Sampling
Low-rank tensor decomposition generalizes low-rank matrix approximation and is a powerful technique for discovering low-dimensional structure in high-dimensional data.
Faster Graph Embeddings via Coarsening
As computing Schur complements is expensive, we give a nearly-linear time algorithm that generates a coarsened graph on the relevant vertices that provably matches the Schur complement in expectation in each iteration.
Edge-Weighted Online Bipartite Matching
Online bipartite matching and its variants are among the most fundamental problems in the online algorithms literature.
Data Structures and Algorithms Computer Science and Game Theory
Slow Mixing of Glauber Dynamics for the Six-Vertex Model in the Ordered Phases
We analyze the Glauber dynamics for the six-vertex model with free boundary conditions in the antiferroelectric phase and significantly extend the region for which local Markov chains are known to be slow mixing.
Data Structures and Algorithms Mathematical Physics Mathematical Physics Probability
