Search Results for author:
Found 5 papers, 3 papers with code
Learning Universal Predictors
Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data.
Language Modeling Is Compression
We show that large language models are powerful general-purpose predictors and that the compression viewpoint provides novel insights into scaling laws, tokenization, and in-context learning.
Hierarchical Partitioning Forecaster
Fixing a hierarchical partition $\mathcal H$ and considering any CPF with a partition that can be constructed using elements of $\mathcal H$ we provide two guarantees: first, a generic one that unveils how local online learning determines regret of learning the entire HPF online; second, a concrete instance that considers HPF with linear forecasters (LHPF) and exp-concave losses where we obtain $O(k \log T)$ regret for sequences of length $T$ where $k$ is a measure of complexity for the competing CPF.
Gated Linear Networks
This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs).
Online Learning with Gated Linear Networks
This paper describes a family of probabilistic architectures designed for online learning under the logarithmic loss.
