John Langford

Efficient Forward Architecture Search

2019 · arXiv (Cornell University)

We propose a neural architecture search (NAS) algorithm, Petridish, to iteratively add shortcut connections to existing network layers. The added shortcut connections effectively perform gradient boosting on the augmented layers. The proposed algorithm is motivated …

Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Betting

2020 · arXiv (Cornell University)

Parameter-free stochastic gradient descent (PFSGD) algorithms do not require setting learning rates while achieving optimal theoretical performance. In practical applications, however, there remains an empirical gap between tuned stochastic gradient descent (SGD) and PFSGD. In …

PcLast: Discovering Plannable Continuous Latent States

2023 · arXiv (Cornell University)

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision making, they ignore state reachability, hampering their performance. In this …