Tanja Alderliesten

2 accepted papers

2026

Iterated Population Based Training with Task-Agnostic Restarts

Alexander Chebykin, Tanja Alderliesten, Peter A.N Bosman

ICML 2026poster

Hyperparameter Optimization (HPO) can lift the burden of tuning hyperparameters (HPs) of neural networks. HPO algorithms from the Population Based Training (PBT) family are efficient thanks to dynamically adjusting HPs every few steps of the weight optimization. Recent results indicate that the numb…

Cited by 0 Source ↗Scholar ↗

2023

Multi-Objective Population Based Training

Arkadiy Dushatskiy, Alexander Chebykin, Tanja Alderliesten, Peter Bosman

ICML 2023poster

Population Based Training (PBT) is an efficient hyperparameter optimization algorithm. PBT is a single-objective algorithm, but many real-world hyperparameter optimization problems involve two or more conflicting objectives. In this work, we therefore introduce a multi-objective version of PBT, MO-P…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗