# Scalable Unidirectional Pareto Optimality for Multi-Task Learning with Constraints

Source: [Scalable Unidirectional Pareto Optimality for Multi-Task Learning with Constraints](<https://www.sota2.com/research/paper/68fa6c5b1e209131cea3388c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:08:48.414Z

Authors: Soumyajit Gupta, Gurpreet Singh, Raghu Bollapragada, Matthew Lease

Published: 2021-10-28T21:35:59.000Z

## Abstract

Multi-objective optimization (MOO) problems require balancing competing objectives, often under constraints. The Pareto optimal solution set defines all possible optimal trade-offs over such objectives. In this work, we present a novel method for Pareto-front learning: inducing the full Pareto manifold at train-time so users can pick any desired optimal trade-off point at run-time. Our key insight is to exploit Fritz-John Conditions for a novel guided double gradient descent strategy. Evaluation on synthetic benchmark problems allows us to vary MOO problem difficulty in controlled fashion and measure accuracy vs. known analytic solutions. We further test scalability and generalization in learning optimal neural model parameterizations for Multi-Task Learning (MTL) on image classification. Results show consistent improvement in accuracy and efficiency over prior MTL methods as well as techniques from operations research.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2110.15442>)

[PDF](<https://arxiv.org/pdf/2110.15442.pdf>)