40 citations · 126 across the 27 of their papers we have counts for
8 papers · 1 filter
Efficient Hyperparameter Search for Non-Stationary Model Training
Berivan Isik, Matthew Fahrbach, Dima Kuzmin +4
Online learning is the cornerstone of applications like recommendation and advertising systems, where models continuously adapt to shifting data distributions. Model training for s…
PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
Adel Javanmard, Matthew Fahrbach, Vahab Mirrokni
This work studies algorithms for learning from aggregate responses. We focus on the construction of aggregation sets (called bags in the literature) for event-level loss functions.…
Greedy PIG: Adaptive Integrated Gradients
Kyriakos Axiotis, Sami Abu-al-haija, Lin Chen +2
Deep learning has become the standard approach for most machine learning tasks. While its impact is undeniable, interpreting the predictions of deep learning models from a human pe…
Practical Performance Guarantees for Pipelined DNN Inference
Aaron Archer, Matthew Fahrbach, Kuikui Liu +1
We optimize pipeline parallelism for deep neural network (DNN) inference by partitioning model graphs into stages and minimizing the running time of the bottleneck stage, inclu…
Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems
Benjamin Coleman, Wang-Cheng Kang, Matthew Fahrbach +4
Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of feat…
Learning Rate Schedules in the Presence of Distribution Shift
Matthew Fahrbach, Adel Javanmard, Vahab Mirrokni +1
We design learning rate schedules that minimize regret for SGD-based online learning in the presence of a changing data distribution. We fully characterize the optimal learning rat…
Sequential Attention for Feature Selection
Taisuke Yasuda, MohammadHossein Bateni, Lin Chen +3
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. For neural networks, pr…
Faster Graph Embeddings via Coarsening
Matthew Fahrbach, Gramoz Goranci, Richard Peng +2
Graph embeddings are a ubiquitous tool for machine learning tasks, such as node classification and link prediction, on graph-structured data. However, computing the embeddings for…