84   Show all »
Toggle Poster Visibility
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #1
AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods
Zhiming Zhou · Qingru Zhang · Guansong Lu · Hongwei Wang · Weinan Zhang · Yong Yu
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #2
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions
Matthew MacKay · Paul Vicol · Jonathan Lorraine · David Duvenaud · Roger Grosse
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #3
G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Qi Meng · Shuxin Zheng · Huishuai Zhang · Wei Chen · Qiwei Ye · Zhi-Ming Ma · Nenghai Yu · Tie-Yan Liu
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #4
Learning to Make Analogies by Contrasting Abstract Relational Structure
Felix Hill · Adam Santoro · David GT Barrett · Ari Morcos · Timothy Lillicrap
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #5
Deep Frank-Wolfe For Neural Network Optimization
Leonard Berrada · Andrew Zisserman · M. Pawan Kumar
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #6
Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy
Yuan Xie · Boyi Liu · Qiang Liu · Zhaoran Wang · Yuan Zhou · Jian Peng
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #7
A2BCD: Asynchronous Acceleration with Optimal Complexity
Robert Hannah · Fei Feng · Wotao Yin
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #8
An analytic theory of generalization dynamics and transfer learning in deep linear networks
Andrew Lampinen · Surya Ganguli
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #9
Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
Marton Havasi · Robert Peharz · José Miguel Hernández Lobato
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #10
ANYTIME MINIBATCH: EXPLOITING STRAGGLERS IN ONLINE DISTRIBUTED OPTIMIZATION
Nuwan Ferdinand · Haider Al-Lawati · Stark Draper · Matthew Nokleby
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #11
Towards Understanding Regularization in Batch Normalization
Ping Luo · Xinjiang Wang · wenqi shao · Zhanglin Peng
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #12
A Mean Field Theory of Batch Normalization
Greg Yang · Jeffrey Pennington · Vinay Rao · Jascha Sohl-Dickstein · Samuel S Schoenholz
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #13
Predicting the Generalization Gap in Deep Networks with Margin Distributions
YiDing Jiang · Dilip Krishnan · Hossein Mobahi · Samy Bengio
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #14
An Empirical study of Binary Neural Networks' Optimisation
Milad Alizadeh · Javier Fernández Marqués · Nicholas Lane · Yarin Gal
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #15
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
Vaishnavh Nagarajan · Zico Kolter
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #16
Efficient Training on Very Large Corpora via Gramian Estimation
Walid Krichene · Nicolas Mayoraz · Steffen Rendle · Li Zhang · Xinyang Yi · Lichan Hong · Ed H. Chi · John Anderson
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #17
Small nonlinearities in activation functions create bad local minima in neural networks
Chulhee Yun · Suvrit Sra · Ali Jadbabaie
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #18
Fluctuation-dissipation relations for stochastic gradient descent
Sho Yaida
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #20
The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent Structure
Frederic Koehler · Andrej Risteski
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #21
Optimal Control Via Neural Networks: A Convex Approach
Yize Chen · Yuanyuan Shi · Baosen Zhang
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #22
NOODL: Provable Online Dictionary Learning and Sparse Coding
Sirisha Rambhatla · Xingguo Li · Jarvis Haupt
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #23
Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking
Haichuan Yang · Yuhao Zhu · Ji Liu
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #24
SGD Converges to Global Minimum in Deep Learning via Star-convex Path
Yi Zhou · Junjie Yang · Huishuai Zhang · Yingbin Liang · VAHID TAROKH
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #25
Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
Michael Lutter · Christian Ritter · Jan Peters
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #26
Relaxed Quantization for Discretized Neural Networks
Christos Louizos · Matthias Reisser · Tijmen Blankevoort · Efstratios Gavves · Max Welling
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #27
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
Ben Athiwaratkun · Marc A Finzi · Pavel Izmailov · Andrew G Wilson
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #28
signSGD with Majority Vote is Communication Efficient and Fault Tolerant
Jeremy Bernstein · Jiawei Zhao · Kamyar Azizzadenesheli · Anima Anandkumar
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #29
Preconditioner on Matrix Lie Group for SGD
XI-LIN LI
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #30
A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation
Akhilesh Deepak Gotmare · Nitish Shirish Keskar · Caiming Xiong · richard socher
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #31
Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds
Peng Cao · Yilun Xu · Yuqing Kong · Yizhou Wang
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #32
Rethinking the Value of Network Pruning
Zhuang Liu · Mingjie Sun · Tinghui Zhou · Gao Huang · Trevor Darrell
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #33
Learning Embeddings into Entropic Wasserstein Spaces
Charlie Frogner · Farzaneh Mirzazadeh · Justin Solomon
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #34
Deep Layers as Stochastic Solvers
Adel Bibi · Bernard Ghanem · Vladlen Koltun · Rene Ranftl
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #35
Initialized Equilibrium Propagation for Backprop-Free Training
Peter OConnor · Efstratios Gavves · Max Welling
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #36
Caveats for information bottleneck in deterministic scenarios
Artemy Kolchinsky · Brendan D Tracey · Steven Van Kuyk
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #37
Learning Two-layer Neural Networks with Symmetric Inputs
Rong Ge · Rohith Kuditipudi · Zhize Li · Xiang Wang
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #38
Sparse Dictionary Learning by Dynamical Neural Networks
Tsung-Han Lin · Ping Tak P Tang
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #39
Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutions
Zaiyi Chen · Zhuoning Yuan · Jinfeng Yi · Bowen Zhou · Enhong Chen · Tianbao Yang
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #40
Gradient descent aligns the layers of deep linear networks
Ziwei Ji · Matus Telgarsky
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #41
Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization
Navid Azizan · Babak Hassibi
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #42
Learning Self-Imitating Diverse Policies
Tanmay Gangwani · Qiang Liu · Jian Peng
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #43
On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks
Yukun Ding · Jinglan Liu · Jinjun Xiong · Yiyu Shi
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #44
Adaptive Gradient Methods with Dynamic Bound of Learning Rate
Liangchen Luo · Yuanhao Xiong · Yan Liu · Xu Sun
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #45
Slimmable Neural Networks
Jiahui Yu · Linjie Yang · Ning Xu · Jianchao Yang · Thomas Huang
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #46
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm
Charbel Sakr · Naresh Shanbhag
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #47
The role of over-parametrization in generalization of neural networks
Behnam Neyshabur · Zhiyuan Li · Srinadh Bhojanapalli · Yann LeCun · Nathan Srebro
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #48
Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds
Cenk Baykal · Lucas Liebenwein · Igor Gilitschenski · Dan Feldman · Daniela Rus
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #50
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
Penghang Yin · Jiancheng Lyu · shuai zhang · Stanley J Osher · YINGYONG QI · Jack Xin
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #51
Learning concise representations for regression by evolving networks of trees
William La Cava · Tilak Raj Singh · Srinivas Suri · Srinivas Suri
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #52
Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile
Panayotis Mertikopoulos · Bruno Lecouat · Houssam Zenati · Chuan-Sheng Foo · Vijay Chandrasekhar · Georgios Piliouras
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #53
ACCELERATING NONCONVEX LEARNING VIA REPLICA EXCHANGE LANGEVIN DIFFUSION
Yi Chen · Jinglin Chen · Jing Dong · Jian Peng · Zhaoran Wang
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #54
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Jonathan Frankle · Michael Carbin
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #55
Three Mechanisms of Weight Decay Regularization
Guodong Zhang · Chaoqi Wang · Bowen Xu · Roger Grosse
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #56
Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network
Daehyun Ahn · Dongsoo Lee · Taesu Kim · Jae-Joon Kim
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #57
Quasi-hyperbolic momentum and Adam for deep learning
Jerry Ma · Denis Yarats
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #58
Towards Robust, Locally Linear Deep Networks
Guang-He Lee · David Alvarez-Melis · Tommi Jaakkola
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #59
InfoBot: Transfer and Exploration via the Information Bottleneck
Anirudh Goyal Alias Parth Goyal · Riashat Islam · DJ Strouse · Zafarali Ahmed · Hugo Larochelle · Matthew Botvinick · Sergey Levine · Yoshua Bengio
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #61
Aggregated Momentum: Stability Through Passive Damping
James Lucas · Shengyang Sun · Richard Zemel · Roger Grosse
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #62
From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference
Randall Balestriero · Richard Baraniuk
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #63
Riemannian Adaptive Optimization Methods
Gary Bécigneul · Octavian Ganea
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #64
Regularized Learning for Domain Adaptation under Label Shifts
Kamyar Azizzadenesheli · Anqi Liu · Fanny Yang · Anima Anandkumar
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #65
DeepOBS: A Deep Learning Optimizer Benchmark Suite
Frank Stefan Schneider · Lukas Balles · Philipp Hennig
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #66
Fixup Initialization: Residual Learning Without Normalization
Hongyi Zhang · Yann Dauphin · Tengyu Ma
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #67
Learning sparse relational transition models
Victoria Xia · Zi Wang · Kelsey Allen · Tom Silver · Leslie Kaelbling
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #68
Gradient Descent Provably Optimizes Over-parameterized Neural Networks
Simon Du · Xiyu Zhai · Barnabás Póczos · Aarti Singh
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #69
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
Stanislaw Jastrzebski · Zachary Kenton · Nicolas Ballas · Asja Fischer · Yoshua Bengio · Amos Storkey
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #70
A Kernel Random Matrix-Based Approach for Sparse PCA
Mohamed El Amine Seddik · mohamed Tamaazousti · Romain Couillet
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #71
SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY
Namhoon Lee · Thalaiyasingam Ajanthan · Philip H.S Torr
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #72
Critical Learning Periods in Deep Networks
Alessandro Achille · Matteo Rovere · Stefano Soatto
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #73
Local SGD Converges Fast and Communicates Little
Sebastian Stich
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #74
Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality
Taiji Suzuki
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #75
A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks
Sanjeev Arora · Nadav Cohen · Noah Golowich · Wei Hu
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #76
Analysis of Quantized Models
LU HOU · Ruiliang Zhang · James Kwok
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #77
Adaptive Estimators Show Information Compression in Deep Neural Networks
Ivan Chelombiev · Conor Houghton · Cian O'Donnell
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #78
On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization
Xiangyi Chen · Sijia Liu · Ruoyu Sun · Mingyi Hong
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #79
Theoretical Analysis of Auto Rate-Tuning by Batch Normalization
Sanjeev Arora · Zhiyuan Li · Kaifeng Lyu
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #80
Decoupled Weight Decay Regularization
Ilya Loshchilov · Frank Hutter
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #81
ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA
Jialin Liu · Xiaohan Chen · Zhangyang Wang · Wotao Yin
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #82
Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach
Minhao Cheng · Thong M Le · Pin-Yu Chen · Huan Zhang · Jinfeng Yi · Cho-Jui Hsieh
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #83
Minimum Divergence vs. Maximum Margin: an Empirical Comparison on Seq2Seq Models
Huan Zhang · hai zhao
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #84
Subgradient Descent Learns Orthogonal Dictionaries
Yu Bai · Qijia Jiang · Ju Sun
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #85
ProxQuant: Quantized Neural Networks via Proximal Operators
Yu Bai · Yu-Xiang Wang · Edo Liberty
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #86
Systematic Generalization: What Is Required and Can It Be Learned?
Dzmitry Bahdanau · Shikhar Murty · Mikhail Noukhovitch · Thien H Nguyen · Harm de Vries · Aaron Courville
Poster
Wed May 8th 04:30 -- 06:30 PM @ Great Hall BC #87
Deep Anomaly Detection with Outlier Exposure
Dan Hendrycks · Mantas Mazeika · Thomas Dietterich