Function Space View Of Bounded Weight Norm Networks

Function Space View Of Bounded Weight Norm Networks

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=R-xaKbBeG0U


Duration: 45:00
547 views
10

Suriya Gunasekar (Microsoft Research)
https://simons.berkeley.edu/talks/function-space-view-bounded-weight-norm-networks
Joint IFML/CCSI Symposium



Other Videos By Simons Institute for the Theory of Computing


2021-11-11Worst-Case Robustness in Machine Learning
2021-11-11Computational trade-offs in graph models
2021-11-11Sum-Of-Squares Lower Bound for Statistical Problems
2021-11-10Analyzing Average-Case Complexity by Meta-Complexity
2021-11-10Panel on Achieving Quantum Advantage in the NISQ Era | Quantum Colloquium
2021-11-09On The Hardness Of Average-Case k-SUM
2021-11-09Low-Complexity Cryptography and Simple Hard-to-Learn Functions
2021-11-09Indistinguishability Obfuscation and Learning Problems
2021-11-09Average-Case Hardness Of CSPs
2021-11-08On Breaking Encryption With A Statistical Zero-Knowledge Oracle
2021-11-06Function Space View Of Bounded Weight Norm Networks
2021-11-05The Planted Matching Problem: Sharp Threshold And Infinite-Order Phase Transition
2021-11-05Scalable And Reliable Inference For Probabilistic Modeling
2021-11-04Learning and Optimization with Adaptive Smoothed Adversaries
2021-11-04The Surprising Power Of The Lenstra-Lenstra-Lovasz Algorithm For Noiseless Inference
2021-11-03Yes, Generative Models Are The New Sparsity
2021-11-03Panel on Novel Fault-Tolerant Qubits | Quantum Colloquium
2021-11-03On the Power of Differentiable Learning
2021-11-03Simple Architecture for a Fault-Tolerant Qubit | Quantum Colloquium
2021-11-02A Data-Centric View On Robustness
2021-11-02Finding Large Cliques in Random and Semi-Random Graphs


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Joint IFML/CCSI Symposium
Suriya Gunasekar