cs.LGJul 1, 2026

Loss Smoothing for Stable Adaptation Under Distribution Shift

Authors: Darshan PatilEkaterina LobachevaRazvan PascanuSarath Chandar

Organizations: Chandar Research Lab · Mila – Quebec AI Institute · Université de Montréal · Polytechnique Montréal · Canada CIFAR AI Chair

Abstract

In settings such as fine-tuning and reinforcement learning, neural networks are often adapted under distribution shift. Standard adaptation methods typically optimize the target objective directly, inducing an abrupt change from the source training objective. This abrupt transition can distort learned representations, including features that may still be useful for the new task. We investigate whether a more gradual transition can improve adaptation. We propose loss smoothing, a simple approach that interpolates between the source and target training objectives at the start of adaptation. This smooth transition helps to preserve useful features from the source distribution while still enabling the model to specialize to the target distribution. Across controlled supervised shifts, pretrained vision adaptation, offline-to-online and online reinforcement learning, and language model fine-tuning, we find that loss smoothing consistently improves performance, suggesting that smoother objective transitions are a broadly useful tool for model adaptation.

Explore similar work

CardsList
  1. Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates

    May 19, 2026Parjanya Prajakta Prashant, Jiongli Zhu, Aldan Creo +1Learning RatesCatastrophic Forgetting