Liam Hodgkinson

Multiplicative noise and heavy tails in stochastic optimization

2020 · arXiv (Cornell University)

Although stochastic optimization is central to modern machine learning, the precise mechanisms underlying its success, and in particular, the precise role of the stochasticity, still remain unclear. Modelling stochastic optimization algorithms as discrete random recurrence …

Generalization Guarantees via Algorithm-dependent Rademacher Complexity

2023 · arXiv (Cornell University)

Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms. In this context, there exists information theoretic generalization bounds that involve (various forms of) mutual information, as well …