activity
20182020
most citedPhase Transitions for the Information Bottleneck in Representation Learning

17 citations · 34 across the 3 of their papers we have counts for

collaborators

9 papers

cs.LG2020

Graph Information Bottleneck

Tailin Wu, Hongyu Ren, Pan Li +1

Representation learning of graph-structured data is challenging because both graph structure and node features carry important information. Graph Neural Networks (GNNs) provide an…

cs.LG2020

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

Silviu-Marian Udrescu, Andrew Tan, Jiahai Feng +3

We present an improved method for symbolic regression that seeks to fit data to formulas that are Pareto-optimal, in the sense of having the best accuracy for a given complexity. I…

cs.LG20203 cited

Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning

Tailin Wu

How can we enable machines to make sense of the world, and become better at learning? To approach this goal, I believe viewing intelligence in terms of many integral aspects, and a…

cs.LG202014 cited

Discovering Nonlinear Relations with Minimum Predictive Information Regularization

Tailin Wu, Thomas Breuel, Michael Skuhersky +1

Identifying the underlying directional relations from observational time series with nonlinear interactions and complex relational structures is key to a wide range of applications…

cs.LG202017 cited

Phase Transitions for the Information Bottleneck in Representation Learning

Tailin Wu, Ian Fischer

In the Information Bottleneck (IB), when tuning the relative strength between compression and prediction terms, how do the two terms behave, and what's their relationship with the…

cs.LG2019

Pareto-optimal data compression for binary classification tasks

Max Tegmark, Tailin Wu

The goal of lossy data compression is to reduce the storage cost of a data set while retaining as much information as possible about something () that you care about. For ex…