SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.07766 · ICLR · 2023

Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization

Bo Han, Kaiwen Zhou, James Cheng, Peilin Zhao, Yatao Bian, Yongqiang Chen, Binghui Xie, Bingzhe Wu, Yonggang Zhang, Han Yang, Kaili Ma

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
lfhase/pair canonical 5 of 6
copy not recorded — 1 of 1
Picsart-AI-Research/PAIR-Diffusion extension 0 of 2
MindSpore-scientific-2/code-1 — 0 of 1
FunctionStatusWhere it lives
EPO Ran lfhase/pair/PAIR/pair.py
code served (permissive licence) · get_code("d16a88da846b7682")
SEPO Ran lfhase/pair/PAIR/pair.py
code served (permissive licence) · get_code("8c73c6ae98d61657")
getNumParams Ran lfhase/pair/ColoredMNIST/pair.py
code served (permissive licence) · get_code("28077f9c052f7aed")
get_irm_loss Ran this paper's copy was not recorded; identical code first harvested from zihao-wang/reactionood
pointer only · get_code("fc7bb9ff36d7b1f1")
get_kl_div Ran lfhase/pair/ColoredMNIST/pair.py
code served (permissive licence) · get_code("cb517763d1083872")
pair_selection Ran lfhase/pair/ColoredMNIST/pair.py
code served (permissive licence) · get_code("32a5b544ec6bebb1")
MinNormSolver Not yet run MindSpore-scientific-2/code-1/PACMOO/min_norm_solvers_numpy.py
code served (permissive licence) · get_code("d0aa27294b3dd8c9")
PAIR Not yet run lfhase/pair/PAIR/pair.py
code served (permissive licence) · get_code("eca51e17518810ff")
init_input_canvas_wrapper Not yet run Picsart-AI-Research/PAIR-Diffusion/gradio_demo.py
code served (permissive licence) · get_code("93721419ca48ae8f")
init_ref_canvas_wrapper Not yet run Picsart-AI-Research/PAIR-Diffusion/gradio_demo.py
code served (permissive licence) · get_code("a6787f2913c02b9a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recently, there has been a growing surge of interest in enabling machine learning systems to generalize well to Out-of-Distribution (OOD) data. Most efforts are devoted to advancing optimization objectives that regularize models to capture the underlying invariance; however, there often are compromises in the optimization process of these OOD objectives: i) Many OOD objectives have to be relaxed as penalty terms of Empirical Risk Minimization (ERM) for the ease of optimization, while the relaxed forms can weaken the robustness of the original objective; ii) The penalty terms also require careful tuning of the penalty weights due to the intrinsic conflicts between ERM and OOD objectives. Consequently, these compromises could easily lead to suboptimal performance of either the ERM or OOD objective. To address these issues, we introduce a multi-objective optimization (MOO) perspective to understand the OOD optimization process, and propose a new optimization scheme called PAreto Invariant Risk Minimization (PAIR). PAIR improves the robustness of OOD objectives by cooperatively optimizing with other OOD objectives, thereby bridging the gaps caused by the relaxations. Then PAIR approaches a Pareto optimal solution that trades off the ERM and OOD objectives properly. Extensive experiments on challenging benchmarks, WILDS, show that PAIR alleviates the compromises and yields top OOD performances. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2206.07766")
get_code_for_paper("2206.07766")
have("2206.07766")

Connect an agent — have() is free.