DeepAI AI Chat
Log In Sign Up

MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning

by   Kirshnateja Killamsetty, et al.
The University of Texas at Dallas

Training deep networks and tuning hyperparameters on large datasets is computationally intensive. One of the primary research directions for efficient training is to reduce training costs by selecting well-generalizable subsets of training data. Compared to simple adaptive random subset selection baselines, existing intelligent subset selection approaches are not competitive due to the time-consuming subset selection step, which involves computing model-dependent gradients and feature embeddings and applies greedy maximization of submodular objectives. Our key insight is that removing the reliance on downstream model parameters enables subset selection as a pre-processing step and enables one to train multiple models at no additional cost. In this work, we propose MILO, a model-agnostic subset selection framework that decouples the subset selection from model training while enabling superior model convergence and performance by using an easy-to-hard curriculum. Our empirical results indicate that MILO can train models 3× - 10 × faster and tune hyperparameters 20× - 75 × faster than full-dataset training or tuning without compromising performance.


page 1

page 2

page 3

page 4


AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning

Deep neural networks have seen great success in recent years; however, t...

Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning

Methods for carefully selecting or generating a small set of training da...

GIO: Gradient Information Optimization for Training Dataset Selection

It is often advantageous to train models on a subset of the available tr...

Submodlib: A Submodular Optimization Library

Submodular functions are a special class of set functions which naturall...

What is the best predictor that you can compute in five minutes using a given Bayesian hierarchical model?

The goal of this paper is to provide a way for statisticians to answer t...

Finding High-Value Training Data Subset through Differentiable Convex Programming

Finding valuable training data points for deep neural networks has been ...

Balancing Constraints and Submodularity in Data Subset Selection

Deep learning has yielded extraordinary results in vision and natural la...