Revisiting "Qualitatively Characterizing Neural Network Optimization Problems" von Frankle, Jonathan

Volltext bestellen

Revisiting "Qualitatively Characterizing Neural Network Optimization Problems" von Frankle, Jonathan

Volltext

Dissecting Pruned Neural Networks von Frankle, Jonathan, Bau, David

Volltext bestellen

Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws von Sardana, Nikhil, Portes, Jacob, Doubov, Sasha, Frankle, Jonathan

Volltext bestellen

Type-Directed Synthesis of Products von Frankle, Jonathan

Volltext bestellen

Example-directed synthesis: a type-theoretic interpretation von Frankle, Jonathan, Osera, Peter-Michael, Walker, David, Zdancewic, Steve

Volltext

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks von Frankle, Jonathan, Carbin, Michael

Volltext bestellen

Studying the Consistency and Composability of Lottery Ticket Pruning Masks von Movva, Rajiv, Frankle, Jonathan, Carbin, Michael

Volltext bestellen

What can linear interpolation of neural network loss landscapes tell us? von Vlaar, Tiffany, Frankle, Jonathan

Volltext

Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates von Portes, Jacob, Blalock, Davis, Stephenson, Cory, Frankle, Jonathan

Volltext bestellen

Comparing Rewinding and Fine-tuning in Neural Network Pruning von Renda, Alex, Frankle, Jonathan, Carbin, Michael

Volltext bestellen

Dynamic Masking Rate Schedules for MLM Pretraining von Ankner, Zachary, Saphra, Naomi, Blalock, Davis, Frankle, Jonathan, Leavitt, Matthew L

Volltext bestellen

CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images von Gokaslan, Aaron, Cooper, A. Feder, Collins, Jasmine, Seguin, Landan, Jacobson, Austin, Patel, Mihir, Frankle, Jonathan, Stephenson, Cory, Kuleshov, Volodymyr

Volltext bestellen

The Effect of Data Dimensionality on Neural Network Prunability von Ankner, Zachary, Renda, Alex, Dziugaite, Gintare Karolina, Frankle, Jonathan, Jin, Tian

Volltext bestellen

Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation von Blakeney, Cody, Forde, Jessica Zosa, Frankle, Jonathan, Zong, Ziliang, Leavitt, Matthew L

Volltext bestellen

Pruning's Effect on Generalization Through the Lens of Training and Regularization von Jin, Tian, Carbin, Michael, Roy, Daniel M, Frankle, Jonathan, Dziugaite, Gintare Karolina

Volltext bestellen

Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? von Paul, Mansheej, Chen, Feng, Larsen, Brett W, Frankle, Jonathan, Ganguli, Surya, Dziugaite, Gintare Karolina

Volltext bestellen

Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks von Paul, Mansheej, Larsen, Brett W, Ganguli, Surya, Frankle, Jonathan, Dziugaite, Gintare Karolina

Volltext bestellen

Pruning Neural Networks at Initialization: Why are We Missing the Mark? von Frankle, Jonathan, Dziugaite, Gintare Karolina, Roy, Daniel M, Carbin, Michael

Volltext bestellen

Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws von Sardana, Nikhil, Portes, Jacob, Doubov, Sasha, Frankle, Jonathan

Volltext