NORMALIZATION HELPS TRAINING OF QUANTIZED LSTM (English)
- New search for: Hou, Lu
- New search for: Zhu, Jinhua
- New search for: Kwok, James
- New search for: Gao, Fei
- New search for: Qin, Tao
- New search for: Liu, Tie-Yan
- New search for: Hou, Lu
- New search for: Zhu, Jinhua
- New search for: Kwok, James
- New search for: Gao, Fei
- New search for: Qin, Tao
- New search for: Liu, Tie-Yan
In:
32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 10 of 20
; 7314-7324
;
2020
- Conference paper / Print
-
Title:NORMALIZATION HELPS TRAINING OF QUANTIZED LSTM
-
Contributors:Hou, Lu ( author ) / Zhu, Jinhua ( author ) / Kwok, James ( author ) / Gao, Fei ( author ) / Qin, Tao ( author ) / Liu, Tie-Yan ( author )
-
Conference:NeurIPS ; 33. ; 2019 ; Vancouver, British Columbia
-
Published in:
-
Publisher:
- New search for: Curran Associates, Inc.
-
Place of publication:Red Hook, NY
-
Publication date:2020
-
Type of media:Conference paper
-
Type of material:Print
-
Language:English
-
Source:
The tables of contents are generated automatically and are based on the data records of the individual contributions available in the index of the TIB portal. The display of the Tables of Contents may therefore be incomplete.
- 7160
-
POINTDAN: A MULTI-SCALE 3D DOMAIN ADAPTION NETWORK FOR POINT CLOUD REPRESENTATIONQin, Can / You, Haoxuan / Wang, Lichen / Kuo, C.-C. Jay / Fu, Yun et al. | 2020
- 7172
-
ZO-ADAMM: ZEROTH-ORDER ADAPTIVE MOMENTUM METHOD FOR BLACK-BOX OPTIMIZATIONChen, Xiangyi / Liu, Sijia / Xu, Kaidi / Li, Xingguo / Lin, Xue / Hong, Mingyi / Cox, David et al. | 2020
- 7184
-
NON-STATIONARY MARKOV DECISION PROCESSES, A WORST-CASE APPROACH USING MODEL- BASED REINFORCEMENT LEARNINGLecarpentier, Erwan / Rachelson, Emmanuel et al. | 2020
- 7194
-
DEPTH-FIRST PROOF-NUMBER SEARCH WITH HEURISTIC EDGE COST AND APPLICATION TO CHEMICAL SYNTHESIS PLANNINGKishimoto, Akihiro / Buesser, Beat / Chen, Bei / Botea, Adi et al. | 2020
- 7205
-
TOWARD A CHARACTERIZATION OF LOSS FUNCTIONS FOR DISTRIBUTION LEARNINGHaghtalab, Nika / Musco, Cameron / Waggoner, Bo et al. | 2020
- 7215
-
CORESETS FOR ARCHETYPAL ANALYSISMair, Sebastian / Brefeld, Ulf et al. | 2020
- 7224
-
EMERGENCE OF OBJECT SEGMENTATION IN PERTURBED GENERATIVE MODELSBielski, Adam / Favaro, Paolo et al. | 2020
- 7235
-
OPTIMAL SPARSE DECISION TREESHu, Xiyang / Rudin, Cynthia / Seltzer, Margo et al. | 2020
- 7244
-
ESCAPING FROM SADDLE POINTS ON RIEMANNIAN MANIFOLDSSun, Yue / Flammarion, Nicolas / Fazel, Maryam et al. | 2020
- 7255
-
MULTI-SOURCE DOMAIN ADAPTATION FOR SEMANTIC SEGMENTATIONZhao, Sicheng / Li, Bo / Yue, Xiangyu / Gu, Yang / Xu, Pengfei / Hu, Runbo / Chai, Hua / Keutzer, Kurt et al. | 2020
- 7269
-
LOCALIZED STRUCTURED PREDICTIONCiliberto, Carlo / Bach, Francis / Rudi, Alessandro et al. | 2020
- 7280
-
NONZERO-SUM ADVERSARIAL HYPOTHESIS TESTING GAMESYasodharan, Sarath / Loiseau, Patrick et al. | 2020
- 7291
-
MANIFOLD-REGRESSION TO PREDICT FROM MEG/EEG BRAIN SIGNALS WITHOUT SOURCE MODELINGSabbagh, David / Ablin, Pierre / Varoquaux, Gael / Gramfort, Alexandre / Engemann, Denis A. et al. | 2020
- 7303
-
MODELING TABULAR DATA USING CONDITIONAL GANXu, Lei / Skoularidou, Maria / Cuesta-Infante, Alfredo / Veeramachaneni, Kalyan et al. | 2020
- 7314
-
NORMALIZATION HELPS TRAINING OF QUANTIZED LSTMHou, Lu / Zhu, Jinhua / Kwok, James / Gao, Fei / Qin, Tao / Liu, Tie-Yan et al. | 2020
- 7325
-
TRAJECTORY OF ALTERNATING DIRECTION METHOD OF MULTIPLIERS AND ADAPTIVE ACCELERATIONPoon, Clarice / Liang, Jingwei et al. | 2020
- 7334
-
DEEP SCALE-SPACES: EQUIVARIANCE OVER SCALEWorrall, Daniel / Welling, Max et al. | 2020
- 7347
-
GRU-ODE-BAYES: CONTINUOUS MODELING OF SPORADICALLY-OBSERVED TIME SERIESBrouwer, Edward De / Simm, Jaak / Arany, Adam / Moreau, Yves et al. | 2020
- 7359
-
ESTIMATING CONVERGENCE OF MARKOV CHAINS WITH L-LAG COUPLINGSBiswas, Niloy / Jacob, Pierre E. / Vanetti, Paul et al. | 2020
- 7370
-
LEARNING-BASED LOW-RANK APPROXIMATIONSIndyk, Piotr / Vakilian, Ali / Yuan, Yang et al. | 2020
- 7381
-
IMPLICIT REGULARIZATION IN DEEP MATRIX FACTORIZATIONArora, Sanjeev / Cohen, Nadav / Hu, Wei / Luo, Yuping et al. | 2020
- 7393
-
LIST-DECODABLE LINEAR REGRESSIONKarmalkar, Sushrut / Klivans, Adam / Kothari, Pravesh et al. | 2020
- 7403
-
LEARNING ELEMENTARY STRUCTURES FOR 3D SHAPE GENERATION AND MATCHINGDeprelle, Theo / Groueix, Thibault / Fisher, Matthew / Kim, Vladimir / Russell, Bryan / Aubry, Mathieu et al. | 2020
- 7414
-
ON THE HARDNESS OF ROBUST CLASSIFICATIONGourdeau, Pascale / Kanade, Varun / Kwiatkowska, Marta / Worrell, James et al. | 2020
- 7424
-
FOUNDATIONS OF COMPARISON-BASED HIERARCHICAL CLUSTERINGGhoshdastidar, Debarghya / Perrot, Michaél / Luxburg, Ulrike Von et al. | 2020
- 7435
-
WHAT THE VEC? TOWARDS PROBABILISTICALLY GROUNDED EMBEDDINGSAllen, Carl / Balazevic, Ivana / Hospedales, Timothy et al. | 2020
- 7446
-
MINIMIZERS OF THE EMPIRICAL RISK AND RISK MONOTONICITYLoog, Marco / Viering, Tom / Mey, Alexander et al. | 2020
- 7456
-
EXPLICIT PLANNING FOR EFFICIENT EXPLORATION IN REINFORCEMENT LEARNINGZhang, Liangpeng / Tang, Ke / Yao, Xin et al. | 2020
- 7466
-
LOWER BOUNDS ON ADVERSARIAL ROBUSTNESS FROM OPTIMAL TRANSPORTBhagoji, Arjun Nitin / Cullina, Daniel / Mittal, Prateek et al. | 2020
- 7479
-
NEURAL SPIN FLOWSDurkan, Conor / Bekasov, Artur / Murray, Iain / Papamakarios, George et al. | 2020
- 7491
-
PHASE TRANSITIONS AND CYCLIC PHENOMENA IN BANDITS WITH SWITCHING CONSTRAINTSSimchi-Levi, David / Xu, Yunzong et al. | 2020
- 7501
-
LATENT WEIGHTS DO NOT EXIST: RETHINKING BINARIZED NEURAL NETWORK OPTIMIZATIONHelwegen, Koen / Widdicombe, James / Geiger, Lukas / Liu, Zechun / Cheng, Kwang-Ting / Nusselder, Roeland et al. | 2020
- 7513
-
NONLINEAR SCALING OF RESOURCE ALLOCATION IN SENSORY BOTTLENECKSEdmondson, Laura Rose / Rodriguez, Alejandro Jimenez / Saal, Hannes P. et al. | 2020
- 7523
-
CONSTRAINED REINFORCEMENT LEARNING HAS ZERO DUALITY GAPPaternain, Santiago / Chamon, Luiz / Calvo-Fullana, Miguel / Ribeiro, Alejandro et al. | 2020
- 7534
-
SYMMETRY-ADAPTED GENERATION OF 3D POINT SETS FOR THE TARGETED DISCOVERY OF MOLECULESGebauer, Niklas / Gastegger, Michael / Schütt, Kristof et al. | 2020
- 7547
-
AN ADAPTIVE NEAREST NEIGHBOR RULE FOR CLASSIFICATIONBalsubramani, Akshay / Dasgupta, Sanjoy / Freund, Yoav / Moran, Shay et al. | 2020
- 7557
-
CORESETS FOR CLUSTERING WITH FAIRNESS CONSTRAINTSHuang, Lingxiao / Jiang, Shaofeng / Vishnoi, Nisheeth et al. | 2020
- 7569
-
PERSPECTIVENET: A SCENE-CONSISTENT IMAGE GENERATOR FOR NEW VIEW SYNTHESIS IN INDOOR ENVIRONMENTSNovotny, David / Graham, Ben / Reizenstein, Jeremy et al. | 2020
- 7581
-
MAVEN: MULTI-AGENT VARIATIONAL EXPLORATIONMahajan, Anuj / Rashid, Tabish / Samvelyan, Mikayel / Whiteson, Shimon et al. | 2020
- 7593
-
COMPETITIVE GRADIENT DESCENTSchaefer, Florian / Anandkumar, Anima et al. | 2020
- 7604
-
GLOBALLY CONVERGENT NEWTON METHODS FOR ILL-CONDITIONED GENERALIZED SELF CONCORDANT LOSSESMarteau-Ferey, Ulysse / Bach, Francis / Rudi, Alessandro et al. | 2020
- 7615
-
CONTINUAL UNSUPERVISED REPRESENTATION LEARNINGRao, Dushyant / Visin, Francesco / Rusu, Andrei / Pascanu, Razvan / Teh, Yee Whye / Hadsell, Raia et al. | 2020
- 7626
-
SELF-ROUTING CAPSULE NETWORKSHahn, Taeyoung / Pyeon, Myeongjang / Kim, Gunhee et al. | 2020
- 7636
-
THE ARAMETERIZED COMPLEXITY OF CASCADING PORTFOLIO SCHEDULINGEiben, Eduard / Ganian, Robert / Kanj, Iyad / Szeider, Stefan et al. | 2020
- 7647
-
MAXIMUM EXPECTED HITTING COST OF A MARKOV DECISION PROCESS AND INFORMATIVENESS OF REWARDSDai, Falcon / Walter, Matthew et al. | 2020
- 7656
-
BIPARTITE EXPANDER HOPFIELD NETWORKS AS SELF-DECODING HIGH-CAPACITY ERROR CORRECTING CODESChaudhuri, Rishidev / Fiete, Ha et al. | 2020
- 7668
-
SEQUENCE MODELING WITH UNCONSTRAINED GENERATION ORDEREmelianenko, Dmitrii / Voita, Elena / Serdyukov, Pavel et al. | 2020
- 7680
-
PROBABILISTIC LOGIC NEURAL NETWORKS FOR REASONINGQu, Meng / Tang, Jian et al. | 2020
- 7691
-
A POLYNOMIAL TIME ALGORITHM FOR LOG-CONCAVE MAXIMUM LIKELIHOOD VIA LOCALLY EXPONENTIAL FAMILIESAxelrod, Brian / Diakonikolas, Ilias / Stewart, Alistair / Sidiropoulos, Anastasios / Valiant, Gregory et al. | 2020
- 7704
-
A UNIFYING FRAMEWORK FOR SPECTRUM-PRESERVING GRAPH SPARSIFICATION AND COARSENINGHermsdorff, Gecia Bravo / Gunderson, Lee et al. | 2020
- 7716
-
STOCHASTIC RUNGE-KUTTA ACCELERATES LANGEVIN MONTE CARLO AND BEYONDLi, Xuechen / Wu, Yi / Mackey, Lester / Erdogdu, Murat A. et al. | 2020
- 7729
-
THE IMPLICIT BIAS OF ADAGRAD ON SEPARABLE DATAQian, Qian / Qian, Xiaoyuan et al. | 2020
- 7738
-
ON TWO WAYS TO USE DETERMINANTAL POINT PROCESSES FOR MONTE CARLO INTEGRATIONGautier, Guillaume / Bardenet, Rémi / Valko, Michal et al. | 2020
- 7748
-
LITEEVAL: A COARSE-TO-FINE FRAMEWORK FOR RESOURCE EFFICIENT VIDEO RECOGNITIONWu, Zuxuan / Xiong, Caiming / Jiang, Yu-Gang / Davis, Larrv S. et al. | 2020
- 7758
-
HOW DEGENERATE IS THE PARAMETRIZATION OF NEURAL NETWORKS WITH THE RELU ACTIVATION FUNCTION?Elbrächter, Dennis Maximilian / Berner, Julius / Grohs, Philipp et al. | 2020
- 7770
-
SPIKE-TRAIN LEVEL BACKPROPAGATION FOR TRAINING DEEP RECURRENT SPIKING NEURALZhang, Wenrui / Li, Peng et al. | 2020
- 7782
-
RE-EXAMINATION OF THE ROLE OF LATENT VARIABLES IN SEQUENCE MODELINGLai, Guokun / Dai, Zihang / Yang, Yiming / Yoo, Shinjae et al. | 2020
- 7793
-
MAX-VALUE ENTROPY SEARCH FOR MULTI-OBJECTIVE BAYESIAN OPTIMIZATIONBelakaria, Syrine / Deshwal, Aryan / Doppa, Janardhan Rao et al. | 2020
- 7804
-
STEIN VARIATIONAL GRADIENT DESCENT WITH MATRIX-VALUED KERNELSWang, Dilin / Tang, Ziyang / Bajaj, Chandrajit / Liu, Qiang et al. | 2020
- 7815
-
CROWDSOURCING VIA PAIRWISE CO-OCCURRENCES: IDENTIFIABILITY AND ALGORITHMSIbrahim, Shahana / Fu, Xiao / Kargas, Nikolaos / Huang, Kejun et al. | 2020
- 7826
-
DETECTING OVERFITTING VIA ADVERSARIAL EXAMPLESWerpachowski, Roman / György, András / Szepesvari, Csaba et al. | 2020
- 7837
-
A UNIFIED BELLMAN OPTIMALITY PRINCIPLE COMBINING REWARD MAXIMIZATION AND EMPOWERMENTLeibfried, Felix / Pascual-Díaz, Sergio / Grau-Moya, Jordi et al. | 2020
- 7849
-
SMILE: SCALABLE META INVERSE REINFORCEMENT LEARNING THROUGH CONTEXT- CONDITIONAL POLICIESGhasemipour, Seyed Kamyar Seyed / Gu, Shixiang / Zemel, Richard et al. | 2020
- 7860
-
TOWARDS UNDERSTANDING THE IMPORTANCE OF SHORTCUT CONNECTIONS IN RESIDUAL NETWORKSLiu, Tianyi / Chen, Minshuo / Zhou, Mo / Du, Simon S. / Zhou, Enlu / Zhao, Tuo et al. | 2020
- 7871
-
MODULAR UNIVERSAL REPARAMETERIZATION: DEEP MULTI-TASK LEARNING ACROSS DIVERSE DOMAINSMeyerson, Elliot / Miikkulainen, Risto et al. | 2020
- 7883
-
SOLVING INTERPRETABLE KERNEL DIMENSIONALITY REDUCTIONWu, Chieh / Miller, Jared / Chang, Yale / Sznaier, Mario / Dy, Jennifer et al. | 2020
- 7894
-
INTERACTION HARD THRESHOLDING: CONSISTENT SPARSE QUADRATIC REGRESSION IN SUB-QUADRATIC TIME AND SPACEYang, Shuo / Shen, Yanyao / Sanghavi, Sujay et al. | 2020
- 7905
-
A MODEL TO SEARCH FOR SYNTHESIZABLE MOLECULESBradshaw, John / Paige, Brooks / Kusner, Matt J. / Segler, Marwin / Hernández-Lobato, José Miguel et al. | 2020
- 7918
-
POST TRAINING 4-BIT QUANTIZATION OF CONVOLUTIONAL NETWORKS FOR RAPID-DEPLOYMENTBanner, Ron / Nahshan, Yury / Soudry, Daniel et al. | 2020
- 7927
-
FAST AND FLEXIBLE MULTI-TASK CLASSIFICATION USING CONDITIONAL NEURAL ADAPTIVE PROCESSESRequeima, James / Gordon, Jonathan / Bronskill, John / Nowozin, Sebastian / Turner, Richard E. et al. | 2020
- 7939
-
DIFFERENTIALLY PRIVATE ANONYMIZED HISTOGRAMSSuresh, Ananda Theertha et al. | 2020
- 7950
-
DYNAMIC LOCAL REGRET FOR NON-CONVEX ONLINE FORECASTINGAydore, Sergul / Zhu, Tianhao / Foster, Dean P. et al. | 2020