Coresets for Classification – Simplified and Strengthened
Dec 6, 2021
Speakers
Cameron Musco
Speaker · 0 followers
Anup B. Rao
Speaker · 0 followers
About
We give relative error coresets for training linear classifiers with a broad class of loss functions, including the logistic loss and hinge loss. Our construction achieves (1±ϵ) relative error with Õ(d ·μ_y(X)^2/ϵ^2) points, where μ_y(X) is a natural complexity measure of the data matrix X ∈ℝ^n × d and label vector y ∈{-1,1}^n, introduced by Munteanu et al. 2018. Our result is based on subsampling data points with probabilities proportional to their ℓ_1 Lewis weights. It significantly improves on existing theoretical bounds and performs well in practice, outperforming uniform subsampling along with other importance sampling methods. Our sampling distribution does not depend on the labels, so can be used for active learning. It also does not depend on the specific loss function, so a single coreset can be used in multiple training scenarios.We give relative error coresets for training linear classifiers with a broad class of loss functions, including the logistic loss and hinge loss. Our construction achieves (1±ϵ) relative error with Õ(d ·μ_y(X)^2/ϵ^2) points, where μ_y(X) is a natural complexity measure of the data matrix X ∈ℝ^n × d and label vector y ∈{-1,1}^n, introduced by Munteanu et al. 2018. Our result is based on subsampling data points with probabilities proportional to their ℓ_1 Lewis weights. It significantly improves o…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Adapting to function difficulty and growth conditions in private optimization
Watch later
Hilal Asi, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Stochastic Solutions for Linear Inverse Problems using the Prior Implicit in a Denoiser
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Spacecraft Collision Avoidance with Bayesian Deep Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
On Model Calibration of Long-Tailed Object Detection and Instance Segmentation
Watch later
Tai-Yu Pan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning to Execute (L2E): Efficient Learning of Plan-Conditioned Policies in Robotics
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%