Laura Balzano — Page 9

Laura Balzano April 15, 2010

Generating all rooted trees

Matlab code to enumerate all possible trees on n nodes: I wrote this awhile ago when I needed to enumerate all possible trees that could be formed by a set of n nodes. There are n^(n-1) such trees. This code uses the fact that there is a bijection between these trees and Prufer sequences. Here is tree_enumeration.m, which is a skeleton file for running code on all possible trees, and here is the function for generating the next tree, get_next_tree.m.

Filed Under: Code

Laura Balzano April 1, 2010

Compressed Sensing in Audio Signals

A demo for Compressed Sensing in Audio Signals can be found here, along with matlab code for the examples.
After all, confrontations with uncertainty and risk belong to the essence of life and are the key to prosperity. There may be risks inherent in gambling, but we should not forget pin up that government intervention also involves risk. Coercive measures aimed at eliminating or restricting gambling are at odds with human nature. Lawmakers also need to weigh all the risks when taking decisions.

Ruhtinas lyhyesti suomeksi: Ruhtinas — edut, kolikkopelit, live-pöydät, maksut ja mobiili. Ennen aloitusta: ehdot ja turvallinen pelaaminen.

Filed Under: Code

Laura Balzano September 1, 2007

Blind Calibration

Blind Calibration examples and code can be found here.

Filed Under: Code

Emergent low-rank dynamics at Neurips 2026

October 16, 2026 By Laura Balzano

Our paper on Emergent low-rank training dynamics in nonlinear MLPs has been accepted to Neurips 2026. In the paper, we build from our ICML 2024 paper where we proved that deep linear networks have exactly low-rank training dynamics for the whole trajectory of training for problems with a low-rank target, for example a classification problem with few classes compared to the data dimension. In this current paper, we extend those theoretical results to the setting where the MLP has a nonlinear but smooth activation function. While our theory studies two-layer MLPs where we train only the inner weights, we see empirically that this phenomenon is maintained regardless of the depth of the network. We can then train on a compressed model to get similar accuracy results with a tiny fraction of the trainable parameters. Our key insight in both works is that there is a clever initialization that allows one to train compressed deep networks and maintain similar dynamics (or exactly the same dynamics in the linear case) throughout training. Congratulations especially to Alec Xu for all the hard work he put in to this problem. We hope you’ll come see his poster in Sydney!

Congratulations Can!

August 18, 2026 By Laura Balzano

Congratulations Dr. Can Yaras for successfully defending his PhD in July. His dissertation was titled “Low-dimensional Structures of Learning and Computation in Deep Learning,” including work that is already making an impact in the crowded field of deep learning efficiency and algorithm understanding. He will be moving on to a postdoc at Princeton Language and Intelligence.

Congratulations Alex!

July 10, 2026 By Laura Balzano

I’m so proud of Dr. Alex Ritchie for his excellent PhD defense! His dissertation is titled “Covariate Structure as Weak Supervision in Estimation Problems,” and includes interesting theoretical and empirical results for Supervised PCA as well as learning nonparametric mixtures. We look forward to all the good Dr. Ritchie will certainly do in the world!