firstbacksecondback
672 Results
|
Poster
|
Mon 2:30 |
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification Takashi Ishida · Ikko Yamane · Nontawat Charoenphakdee · Gang Niu · Masashi Sugiyama |
|
|
Poster
|
Tue 2:30 |
Interpretations of Domain Adaptations via Layer Variational Analysis Huan-Hsin Tseng · Hsin-Yi Lin · Kuo-Hsuan Hung · Yu Tsao |
|
|
Poster
|
UL2: Unifying Language Learning Paradigms Yi Tay · Mostafa Dehghani · Vinh Tran · Xavier Garcia · Jason Wei · Xuezhi Wang · Hyung Won Chung · Dara Bahri · Tal Schuster · Huaixiu Steven Zheng · Denny Zhou · Neil Houlsby · Donald Metzler |
||
|
Oral
|
Wed 6:30 |
Encoding Recurrence into Transformers Feiqing Huang · Kexin Lu · Yuxi Cai · Zhen Qin · Yanwen Fang · Guangjian Tian · Guodong Li |
|
|
Poster
|
Wed 7:30 |
Encoding Recurrence into Transformers Feiqing Huang · Kexin Lu · Yuxi Cai · Zhen Qin · Yanwen Fang · Guangjian Tian · Guodong Li |
|
|
Poster
|
Mon 2:30 |
Fisher-Legendre (FishLeg) optimization of deep neural networks Jezabel R. Garcia · Federica Freddi · Stathi Fotiadis · Maolin Li · Sattar Vakili · Alberto Bernacchia · Guillaume Hennequin |
|
|
Oral
|
Mon 1:10 |
Fisher-Legendre (FishLeg) optimization of deep neural networks Jezabel R. Garcia · Federica Freddi · Stathi Fotiadis · Maolin Li · Sattar Vakili · Alberto Bernacchia · Guillaume Hennequin |
|
|
Poster
|
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints Aran Komatsuzaki · Joan Puigcerver · James Lee-Thorp · Carlos Riquelme · Basil Mustafa · Joshua Ainslie · Yi Tay · Mostafa Dehghani · Neil Houlsby |
||
|
Workshop
|
On Gradients of Deep Generative Models for Representation-Invariant Anomaly Detection Sam Dauncey · Christopher Holmes · Christopher Williams · Fabian Falck |
||
|
Poster
|
Tue 2:30 |
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? Mansheej Paul · Feng Chen · Brett Larsen · Jonathan Frankle · Surya Ganguli · Gintare Karolina Dziugaite |
|
|
Poster
|
Mon 2:30 |
Neural Networks and the Chomsky Hierarchy Gregoire Deletang · Anian Ruoss · Jordi Grau-Moya · Tim Genewein · Li Kevin Wenliang · Elliot Catt · Chris Cundy · Marcus Hutter · Shane Legg · Joel Veness · Pedro Ortega |
|
|
Poster
|
Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy Jinsong Zhang · Qiang Fu · Xu Chen · Lun Du · Zelin Li · Gang Wang · Xiaoguang Liu · Shi Han · Dongmei Zhang |