Publications

Preprints:

• "PCA recovery thresholds in low-rank matrix inference with sparse noise", Adomaityte, U., Sicuro, G., Vivo, P., arxiv

Peer-reviewed:

• "High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality", Adomaityte, U., Defilippis, L., Loureiro, B., Sicuro, G., J. Stat. Mech. Machine Learning 2024 Special Issue (2024), also HeavyTails Workshop paper at NeurIPS 2023 [J.Stat.Mech. arxiv]

• "Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach", Adomaityte, U., Sicuro, G., Vivo, P., NeurIPS 2023 main track [NeurIPS arxiv]

• "Planted matching problems on random hypergraphs", Adomaityte, U., Toshniwal, A., Sicuro, G., Zdeborová, L. (2022). Physical Review E [paper arxiv]

Workshop papers:

• "Unveiling the Hessian’s Connection to the Decision Boundary", Sabanayagam, M., Behrens, F., Adomaityte, U., Dawid, A., M3L Workshop paper at NeurIPS 2023, [arxiv]

Lecture notes:

• "Replica method for computational problems with randomness: principles and illustrations", J Steinberg, U Adomaitytė, A Fachechi, P Mergny, D Barbier and R Monasson, J. Stat. Mech. (2024), Special Issue for the Summer school on Statistical Physics & Machine learning, Les Houches 2022, [J.Stat.Mech. free access].