27 citations · 85 across the 17 of their papers we have counts for
9 papers · 1 filter
Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track
Rylan Schaeffer, Joshua Kazdan, Yegor Denisov-Blanch +11
Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of…
Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation
Cody Blakeney, Jessica Zosa Forde, Jonathan Frankle +2
Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning prac…
Does DQN really learn? Exploring adversarial training schemes in Pong
Bowen He, Sreehari Rammohan, Jessica Forde +1
In this work, we study two self-play training schemes, Chainer and Pool, and show they lead to improved agent performance in Atari Pong compared to a standard DQN agent -- trained…
Model Selection's Disparate Impact in Real-World Deep Learning Applications
Jessica Zosa Forde, A. Feder Cooper, Kweku Kwegyir-Aggrey +2
Algorithmic fairness has emphasized the role of biased data in automated decision outcomes. Recently, there has been a shift in attention to sources of bias that implicate fairness…
Hyperparameter Optimization Is Deceiving Us, and How to Stop It
A. Feder Cooper, Yucheng Lu, Jessica Zosa Forde +1
Recent empirical work shows that inconsistent results based on choice of hyperparameter optimization (HPO) configuration are a widespread problem in ML research. When comparing two…
Bespoke vs. Prêt-à-Porter Lottery Tickets: Exploiting Mask Similarity for Trainable Sub-Network Finding
Michela Paganini, Jessica Zosa Forde
The observation of sparse trainable sub-networks within over-parametrized networks - also known as Lottery Tickets (LTs) - has prompted inquiries around their trainability, scaling…
Streamlining Tensor and Network Pruning in PyTorch
Michela Paganini, Jessica Forde
In order to contrast the explosion in size of state-of-the-art machine learning models that can be attributed to the empirical advantages of over-parametrization, and due to the ne…
On Iterative Neural Network Pruning, Reinitialization, and the Similarity of Masks
Michela Paganini, Jessica Forde
We examine how recently documented, fundamental phenomena in deep learning models subject to pruning are affected by changes in the pruning procedure. Specifically, we analyze diff…
The Scientific Method in the Science of Machine Learning
Jessica Zosa Forde, Michela Paganini
In the quest to align deep learning with the sciences to address calls for rigor, safety, and interpretability in machine learning systems, this contribution identifies key missing…