← Search

Jared Q Davis

2 accepted papers

2021

Catformer: Designing Stable Transformers via Sensitivity Analysis

ICML 2021spotlight

Transformer architectures are widely used, but training them is non-trivial, requiring custom learning rate schedules, scaling terms, residual connections, careful placement of submodules such as normalization, and so on. In this paper, we improve upon recent analysis of Transformers and formalize a…

Cited by 22SourcePDFScholar
2021

Debiasing a First-order Heuristic for Approximate Bi-level Optimization

ICML 2021spotlight

Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications across deep learning, it suffers from time and memory complexity proportional to the length $r$ of its inner optimization l…