22 citations · 71 across the 18 of their papers we have counts for
3 papers · 1 filter
The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization
Daniel LeJeune, Hamid Javadi, Richard G. Baraniuk
Among the most successful methods for sparsifying deep (neural) networks are those that adaptively mask the network weights throughout training. By examining this masking, or dropo…
Extreme Compressed Sensing of Poisson Rates from Multiple Measurements
Pavan K. Kota, Daniel LeJeune, Rebekah A. Drezek +1
Compressed sensing (CS) is a signal processing technique that enables the efficient recovery of a sparse high-dimensional signal from low-dimensional measurements. In the multiple…
The Common Intuition to Transfer Learning Can Win or Lose: Case Studies for Linear Regression
Yehuda Dar, Daniel LeJeune, Richard G. Baraniuk
We study a fundamental transfer learning process from source to target linear regression tasks, including overparameterized settings where there are more learned parameters than da…