Theory of Computation (TOC) Seminars
 |
TBA Tuesday, May 6, 2025 - 4:15pm to 5:15pm TBA |
 |
TBA Tuesday, April 15, 2025 - 4:15pm to 5:15pm TBA |
 |
How to Securely Implement Cryptography in Deep Neural Networks Tuesday, April 22, 2025 - 4:15pm to 5:15pm The wide adoption of deep neural networks (DNNs) raises the question of how can we equip them with a desired cryptographic functionality (e.g., to decr |
 |
Simulating Time With Square-Root Space Tuesday, April 8, 2025 - 4:15pm to 5:15pm |
 |
Rapid Mixing at the Uniqueness Threshold Tuesday, March 18, 2025 - 4:15pm to 5:15pm Over the past decades, a fascinating computational phase transition has been identified in sampling from Gibbs distributions. |
 |
Overparametrized systems: from Smale's 17th problem to two-layer neural networks Tuesday, March 11, 2025 - 4:15pm to 5:15pm Training modern machine learning models requires to optimize highly non-convex risk function and yet simple gradient-based methods are able to find global minima for very high-dimensional problems. |
 |
Pseudorandom Correlation Generators Tuesday, March 4, 2025 - 4:15pm to 5:15pm Correlated secret randomness is an important resource for many cryptographic applications. |
 |
Good Locally Testable Codes Tuesday, February 25, 2025 - 4:15pm to 5:15pm An error-correcting code is locally testable (LTC) if there is a random tester that reads only a small number of bits of a given word and decides whether the word is in the code, or at least close to it. |
 |
On the Complexity of Neural Computation in Superposition Tuesday, February 18, 2025 - 4:15pm to 5:15pm Recent advances in neural networks interpretability suggest that superposition, the ability of a network to represent many more features than it has neurons, is a key mechanism underlying how neural networks compute. |
 |
"Local-to-Global" Theorems on High Dimensional Expanders Tuesday, February 11, 2025 - 4:15pm to 5:15pm |
Pages
