ICML 2025 Presentations

Check the ICML 2025 Presentations from our group!

Main Meeting

1. Adaptive kernel predictors from feature-learning infinite limits of neural networks

Clarissa Lauditi · Blake Bordelon · Cengiz Pehlevan

East Exhibition Hall A-B #E-2108

Tue 15 Jul 4:30 p.m. PDT — 7 p.m. PDT
 

2. A Model of Place Field Reorganization During Reward Maximization

M Ganesh Kumar · Blake Bordelon · Jacob A Zavatone-Veth · Cengiz Pehlevan

West Exhibition Hall B2-B3 #W-309

Wed 16 Jul 11 a.m. PDT — 1:30 p.m. PDT
 

3. Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer

Blake Bordelon · Cengiz Pehlevan

East Exhibition Hall A-B #E-2101

Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT
 

4. Risk and cross validation in ridge regression with correlated samples

Alexander Atanasov · Jacob A Zavatone-Veth · Cengiz Pehlevan

East Exhibition Hall A-B #E-2306

Thu 17 Jul 11 a.m. PDT — 1:30 p.m. PDT
 

5. No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions

Benjamin Ruben · William Tong · Hamza Chaudhry · Cengiz Pehlevan

West Exhibition Hall B2-B3 #W-1018

Thu 17 Jul 4:30 p.m. PDT — 7 p.m. PDT

Workshops

6. Two-point deterministic equivalence for SGD in random feature models

Alexander Atanasov, Blake Bordelon, Jacob A Zavatone-Veth, Courtney Paquette, Cengiz Pehlevan

HiLD at ICML 2025 Poster