ICML 2019 Workshop Deep Phenomena Submissions

Scaling characteristics of sequential multitask learning: Networks naturally learn to learn
Guy Davidson, Michael C. Mozer
- Published: 04 Jun 2019, Last Modified: 05 May 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
Adversarial Training Can Hurt Generalization
Aditi Raghunathan*, Sang Michael Xie*, Fanny Yang, John Duchi, Percy Liang
- Published: 04 Jun 2019, Last Modified: 05 May 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
Grassmannian initialization: Neural network initialization using sub-space packing
Vinay Uday Prabhu, Dian Ang Yap
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Evaluating the distribution learning capabilities of GANs
Amit Rege, Claire Monteleoni
- 28 May 2019 (modified: 22 Oct 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Garbage in, model out: Weight theft with just noise
Vinay Uday Prabhu, Nick Roberts, Matthew McAteer
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Examining Interpretable Feature Relationships in Deep Networks for Action recognition
Mathew Monfort, Kandan Ramakrishnan, Barry A McNamara, Alex Lascelles, Dan Gutfreund, Rogerio Feris, Aude Oliva
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
The Effect of Network Depth on the Optimization Landscape
Behrooz Ghorbani, Ying Xiao, Shankar Krishnan
- 28 May 2019 (modified: 05 May 2023)
- ICML Deep Phenomena 2019
- Readers: Everyone
SuperTML: Two-Dimensional Word Embedding and Transfer Learning Using ImageNet Pretrained CNN Models for the Classifications on Tabular Data
Baohua Sun, Lin Yang, Wenhan Zhang, Michael Lin, Patrick Dong, Charles Young and Jason Dong,
- 28 May 2019 (modified: 22 Oct 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding
Baohua Sun, Lin Yang, Michael Lin, Charles Young, Patrick Dong, Wenhan Zhang, and Jason Dong
- 28 May 2019 (modified: 22 Oct 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
A Systematic Framework for Natural Perturbations from Videos
Vaishaal Shankar, Achal Dave, Rebecca Roelofs, Deva Ramanan, Benjamin Recht, Ludwig Schmidt
- Published: 04 Jun 2019, Last Modified: 22 Oct 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
Probing emergent geometry in speech models via replica theory
Suchismita Padhy, Jenelle Feather, Cory Stephenson, Oguz Elibol, Hanlin Tang, Josh McDermott, Sueyeon Chung
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
Fanny Yang, Zuowen Wang, Christina Heinze-Deml
- Published: 04 Jun 2019, Last Modified: 05 May 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
Do LSTMs Learn Compositionally?
Naomi Saphra, Adam Lopez
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Evolution of Eigenvalue Decay in Deep Networks
Lukas Pfahler, Katharina Morik
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Using effective dimension to analyze feature transformations in deep neural networks
Kavya Ravichandran, Ajay Jain, Alexander Rakhlin
- Published: 04 Jun 2019, Last Modified: 05 May 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
Better Generalization with Adaptive Adversarial Training
Amit Despande, Sandesh Kamath, K V Subrahmanyam
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Bad Global Minima Exist and SGD Can Reach Them
Shengchao Liu, Dimitris Papailiopoulos, Dimitris Achlioptas
- Published: 04 Jun 2019, Last Modified: 22 Oct 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
Simplicity bias in the parameter-function map of deep neural networks
Guillermo Valle-Pérez, Chico Q. Camargo, Ard A. Louis
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Spectral Analysis of Kernel and Neural Embeddings: Optimization and Generalization
Emilio Jorge, Morteza Haghir Chehreghani, Devdatt Dubhashi
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
A Neuro-AI Interface: Learning DNNs from the Human Brain
Zhengwei Wang, Qi She, Eoin Brophy, Alan F. Smeaton, Tomas E. Ward, Graham Healy
- 28 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Sparsity Emerges Naturally in Neural Language Models
Naomi Saphra, Adam Lopez
- Published: 04 Jun 2019, Last Modified: 05 May 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
On the Importance of Full Rank Initializations in Deep Neural Networks
Vaibhav B Sinha*, Vishwak Srinivasan*, Vineeth N B
- 17 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone
Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
Hattie Zhou, Janice Lan, Rosanne Liu, Jason Yosinski
- Published: 04 Jun 2019, Last Modified: 22 Oct 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
Angular Visual Hardness
Beidi Chen, Weiyang Liu, Animesh Garg, Zhiding Yu, Anshumali Shrivastava, Anima Anandkumar
- Published: 04 Jun 2019, Last Modified: 05 May 2023
- ICML Deep Phenomena 2019
- Readers: Everyone
Universality Patterns in the Training of Neural Networks
Raghav Somani, Navin Goyal, Prateek Jain, Praneeth Netrapalli
- 17 May 2019 (modified: 05 May 2023)
- Submitted to ICML Deep Phenomena 2019
- Readers: Everyone