5 accepted papers
Various types of learning rate (LR) schedulers are being used for training or fine tuning of Large Language Models today. In practice, several mid-flight changes are required in the LR schedule either manually, or with careful choices around warmup steps, peak LR, type of decay and restarts. To stud…
Invariance (defined in a general sense) has been one of the most effective priors for representation learning. Direct factorization of parametric models is feasible only for a small range of invariances, while regularization approaches, despite improved generality, lead to nonconvex optimization. In…
Invariance is an effective prior that has been extensively used to bias supervised learning with a \emph{given} representation of data. In order to learn invariant representations, wavelet and scattering based methods “hard code” invariance over the \emph{entire} sample space, hence restricted to a…
Latent prediction models, exemplified by multi-layer networks, employ hidden variables that automate abstract feature discovery. They typically pose nonconvex optimization problems and effective semi-definite programming (SDP) relaxations have been developed to enable global solutions (Aslan et al.,…
Unsupervised learning of structured predictors has been a long standing pursuit in machine learning. Recently a conditional random field auto-encoder has been proposed in a two-layer setting, allowing latent structured representation to be automatically inferred. Aside from being nonconvex, it als…