Andrej Risteski
@andrejristeski.bsky.social
Machine learning researcher. Professor in ML department at CMU.
Reposted by Andrej Risteski
Announcing the 7th Learning Theory Alliance mentoring workshop on November 20. Fully free & virtual!
Theme: Harnessing AI for Research, Learning, and Communicating
Ft @aaroth.bsky.social @andrejristeski.bsky.social @profericwong.bsky.social @ktalwar.bsky.social &more
Theme: Harnessing AI for Research, Learning, and Communicating
Ft @aaroth.bsky.social @andrejristeski.bsky.social @profericwong.bsky.social @ktalwar.bsky.social &more
November 7, 2025 at 4:34 PM
Announcing the 7th Learning Theory Alliance mentoring workshop on November 20. Fully free & virtual!
Theme: Harnessing AI for Research, Learning, and Communicating
Ft @aaroth.bsky.social @andrejristeski.bsky.social @profericwong.bsky.social @ktalwar.bsky.social &more
Theme: Harnessing AI for Research, Learning, and Communicating
Ft @aaroth.bsky.social @andrejristeski.bsky.social @profericwong.bsky.social @ktalwar.bsky.social &more
If you're coming to COLT, @khodakmoments.bsky.social , @tm157.bsky.social, myself, Nick Boffi and Jianfeng Lu are organizing a workshop on the Theory of AI for Scientific Computing, to be held on the first day of the conference (Monday, June 30). Schedule here: tasc-workshop.github.io/#schedule
June 29, 2025 at 1:17 AM
If you're coming to COLT, @khodakmoments.bsky.social , @tm157.bsky.social, myself, Nick Boffi and Jianfeng Lu are organizing a workshop on the Theory of AI for Scientific Computing, to be held on the first day of the conference (Monday, June 30). Schedule here: tasc-workshop.github.io/#schedule
In recent work arxiv.org/abs/2410.09867 with D. Rohatgi, @tm157.bsky.social, @zacharylipton.bsky.social , J. Lu and A. Moitra, we revisit fine-grained expressiveness in GNNs---beyond the usual symmetry (Weisfeiler-Lehman) lens. Paper will appear in ICML '25, thread below.
Towards characterizing the value of edge embeddings in Graph Neural Networks
Graph neural networks (GNNs) are the dominant approach to solving machine learning problems defined over graphs. Despite much theoretical and empirical work in recent years, our understanding of finer...
arxiv.org
June 24, 2025 at 3:54 PM
In recent work arxiv.org/abs/2410.09867 with D. Rohatgi, @tm157.bsky.social, @zacharylipton.bsky.social , J. Lu and A. Moitra, we revisit fine-grained expressiveness in GNNs---beyond the usual symmetry (Weisfeiler-Lehman) lens. Paper will appear in ICML '25, thread below.