This year marks the fortieth International Conference on Machine Learning (ICML). Supported by the International Machine Learning Society, ICML is one of the biggest, and most prestigious, academic conferences for artificial intelligence. This year’s conference took place from July 23rd through 29th at the Hawaii Convention Center, as well as virtually. This year CAIDA had ten members with papers accepted for ICML. A big congratulations to our members and their teams for their success! You can see the CAIDA papers below, and the remainder of ICML’s selections here.
Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole
Knowledge Hypergraph Embedding Meets Relational Algebra
Devon Graham, Kevin Leyton-Brown, Tim Roughgarden
Formalizing Preferences Over Runtime Distributions
Brian Irwin, Eldad Haber, Raviv Gal, Avi Ziv
Neural Network Accelerated Implicit Filtering: Integrating Neural Network Surrogates With Provably Convergent Derivative Free Optimization Methods
Jonathan Lavington, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Nicolas Le Roux
Target-based Surrogates for Stochastic Optimization
Xiaoxiao Li, Zhao Song, Jiaming Yang
Federated Adversarial Learning: A Framework with Convergence Analysis
Wu Lin, Valentin Duruisseaux, Melvin Leok, Frank Nielsen, Khan Emtiyaz, Mark Schmidt
Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning
Mohamad Amin Mohamadi, Won Bae, Danica J Sutherland
A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel
Andreas Munk, Alexander Mead, Frank Wood
Uncertain Evidence in Probabilistic Models and Stochastic Simulators
Julie Nutini, Issam Laradji, Mark Schmidt
Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence
Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi, Christos Thrampoulidis
On the Role of Attention in Prompt-tuning
Hamed Shirzad, Ameya Velingker, Balaji Venkatachalam, Danica J Sutherland, Ali K Sinop
Exphormer: Sparse Transformers for Graphs
Christian Weilbach, William Harvey, Frank Wood
Graphically Structured Diffusion Models
Zuheng Xu, Naitong Chen, Trevor Campbell
MixFlows: principled variational inference via mixed flows
Note: All CAIDA Members have been bolded and a link has been provided to their personal webpages