- Machine Learning for Big Data in the CloudAuthors: Carlos Guestrin
- High-dimensional Sampling AlgorithmsAuthors: Santosh Vempala
- Acoustic Modeling and Deep LearningAuthors: Vincent Vanhoucke
Deep Learning 1
- On autoencoder scoringAuthors: Hanna Kamyshanska; Roland Memisevic
- On the difficulty of training Recurrent Neural NetworksAuthors: Razvan Pascanu; Tomas Mikolov; Yoshua Bengio
- Maxout NetworksAuthors: Ian Goodfellow; David Warde-Farley; Mehdi Mirza; Aaron Courville; Yoshua Bengio
- Collaborative hyperparameter tuningAuthors: R
- Learning mid-level representations of objects by harnessing the aperture problemAuthors: Roland Memisevic; Georgios Exarchakis
- Approximation properties of DBNs with binary hidden units and real-valued visible unitsAuthors: Oswin Krause; Asja Fischer; Tobias Glasmachers; Christian Igel
- Better Mixing via Deep RepresentationsAuthors: Yoshua Bengio; Gregoire Mesnil; Yann Dauphin; Salah Rifai
- Fast dropout trainingAuthors: Sida Wang; Christopher Manning
Track A: Online Learning 2
- Optimal Regret Bounds for Selecting the State Representation in Reinforcement LearningAuthors: Odalric-Ambrym Maillard; Phuong Nguyen; Ronald Ortner; Daniil Ryabko
- Combinatorial Multi-Armed Bandit: General Framework, Results and ApplicationsAuthors: Wei Chen; Yajun Wang; Yang Yuan
- Dynamical Models and tracking regret in online convex programmingAuthors: Eric Hall; Rebecca Willett
- Better Rates for Any Adversarial Deterministic MDPsAuthors: Ofer Dekel; Elad Hazan
- Multiple Identifications in Multi-Armed BanditsAuthors: Sebastian Bubeck; Tengyao Wang; Nitin Viswanathan
- Gossip-based distributed stochastic bandit algorithmsAuthors: Balazs Szorenyi; Robert Busa-Fekete; Istvan Hegedus; Robert Ormandi; Mark Jelasity; Balazs Kegl
- Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier MethodAuthors: Taiji Suzuki
Track A: Crowd Sourcing and Large Scale Learning
- Optimistic Knowledge Gradient Policy for Optimal Budget Allocation in CrowdsourcingAuthors: Xi Chen; Qihang Lin; Dengyong Zhou
- Quantile Regression for Large-scale ApplicationsAuthors: Jiyan Yang; Xiangrui Meng; Michael Mahoney
- Distributed Training of Large-scale Logistic Models,Authors: Siddharth Gopal; Yiming Yang
- Label Partitioning For Sublinear Ranking,Authors: Jason Weston; Ameesh Makadia; Hector Yee
- Human BoostingAuthors: Harsh Pareek; Pradeep Ravikumar
- Large-Scale Learning with Less RAM via RandomizationAuthors: Daniel Golovin; D. Sculley; Brendan McMahan; Michael Young
- Robust Regression on MapReduceAuthors: Xiangrui Meng; Micheal W. Mahoney
- Adaptive Task Assignment for Crowdsourced ClassificationAuthors: Chien-Ju Ho; Shahin Jabbari; Jennifer Wortman Vaughan
Compressed Sensing 1
- Feature Selection in High-Dimensional ClassificationAuthors: Mladen Kolar; Han Liu
- Exact Rule Learning via Boolean Compressed SensingAuthors: Dmitry Malioutov; Kush Varshney
- Sparse Recovery under Linear TransformationAuthors: Ji Liu; Lei Yuan; Jieping Ye
- Noisy and Missing Data Regression: Distribution-Oblivious Support RecoveryAuthors: Yudong Chen; Constantine Caramanis
Track B: Structured Labeling
- Learning from Human-Generated ListsAuthors: Kwang-Sung Jun; Jerry Zhu; Burr Settles; Timothy Rogers
- A Structural SVM Based Approach for Optimizing Partial AUCAuthors: Harikrishna Narasimhan; Shivani Agarwal
- A Machine Learning Framework for Programming by ExampleAuthors: Aditya Menon; Omer Tamuz; Sumit Gulwani; Butler Lampson; Adam Kalai
- Convex Adversarial Collective ClassificationAuthors: Mohamad Ali Torkamani; Daniel Lowd
- Learning Convex QP Relaxations for Structured PredictionAuthors: Jeremy Jancsary; Sebastian Nowozin; Carsten Rother
- Fixed-Point Model For Structured LabelingAuthors: Quannan Li; Jingdong Wang; David Wipf; Zhuowen Tu
- A Generalized Kernel Approach to Structured Output LearningAuthors: Hachem Kadri; Mohammad Ghavamzadeh; Philippe Preux
- Optimizing the F-measure in Multi-label Classification: Plug-in Rule Approach versus Structured Loss MinimizationAuthors: Krzysztof Dembczynski; Wojciech Kotlowski; Arkadiusz Jachnik; Willem Waegeman; Eyke Huellermeier
Track B: Kernel Methods
- Fastfood - Computing Hilbert Space Expansions in loglinear timeAuthors: Quoc Le; Tamas Sarlos; Alexander Smola
- Reproducing kernel Hilbert spaces are not closed under many operationsAuthors:
- Domain Adaptation under Target and Conditional Shift,Authors: Kun Zhang; Bernhard Schoelkopf; Krikamol Muandet; Zhikun Wang
- Learning Optimally Sparse Support Vector MachinesAuthors: Andrew Cotter; Shai Shalev-Shwartz; Nati Srebro
- A New Frontier of Kernel Design for Structured Data,Authors: Kilho Shin
- Characterizing the Representer TheoremAuthors: Yaoliang Yu; Hao Cheng; Dale Schuurmans; Csaba Szepesvari
- Covariate Shift in Hilber Space: A Solution Via Sorrogate KernelsAuthors: Kai Zhang; Vincent Zheng; QIaojun Wang; James Kwok; Qiang Yang
Reinforcement Learning 1
- Learning Policies for Contextual Submodular PredictionAuthors: Stephane Ross; Jiaji Zhou; Yisong Yue; Debadeepta Dey; Drew Bagnell
- Learning an Internal Dynamics Model from Control DemonstrationAuthors: Matthew Golub; Steven Chase; Byron Yu
- Safe Policy IterationAuthors: Matteo Pirotta; Marcello Restelli; Alessio Pecorino; Daniele Calandriello
- Temporal Difference Methods for the Variance of the Reward To GoAuthors: Aviv Tamar; Dotan Di Castro; Shie Mannor
- Value Iteration with incremental representation learning for continuous POMDPsAuthors: Sebastian Brechtel; Tobias Gindele; R diger Dillmann
- The Sample-Complexity of General Reinforcement LearningAuthors: Tor Lattimore; Marcus Hutter; Peter Sunehag
- Online Feature Selection for Model-based Reinforcement LearningAuthors: Trung Nguyen; Zhuoru Li; Tomi Silander; Tze Yun Leong
- Bayesian Learning of Recursively Factored EnvironmentsAuthors: Marc Bellemare; Joel Veness; Michael Bowling
Track C: Dimensionality Reduction
- Principal Component Analysis on non-Gaussian Dependent DataAuthors: Fang Han; Han Liu
- Deep Canonical Correlation AnalysisAuthors: Galen Andrew; Jeff Bilmes; Raman Arora; Karen Livescu
- Canonical Correlation Analysis based on Hilbert-Schmidt Independence Criterion and Centered Kernel Target AlignmentAuthors: Billy Chang; Uwe Kruger; Rafal Kustra; Junping Zhang
- Vanishing Component AnalysisAuthors: Roi Livni; David Lehavi; Sagi Schein; Hila Nachliely; Shai Shalev-Shwartz; Amir Globerson
- Fast algorithms for sparse principal component analysis based on Rayleigh quotient iterationAuthors: Volodymyr Kuleshov
- Efficient Dimensionality Reduction for Canonical Correlation AnalysisAuthors: Haim Avron; Christos Boutsidis ; Sivan Toledo ; Anastasios Zouzias
- Adaptive Sparsity in Gaussian Graphical ModelsAuthors: Eleanor Wong; Suyash Awate; P. Thomas Fletcher
- The Most Generative Maximum Margin Bayesian NetworksAuthors: Robert Peharz; Sebastian Tschiatschek; Franz Pernkopf
Track D: Learning Theory 3
- Activized Learning with Uniform Classification NoiseAuthors: Liu Yang; Steve Hanneke
- Efficient Active Learning of Halfspaces: an Aggressive ApproachAuthors: Alon Gonen; Sivan Sabato; Shai Shalev-Shwartz
- Selective sampling algorithms for cost-sensitive multiclass predictionAuthors: Alekh Agarwa
- Generic Exploration and K-armed Voting BanditsAuthors: Tanguy Urvoy; Fabrice Clerot; Raphael Feraud; Sami Naamane
- Efficient Semi-supervised and Active Learning of DisjunctionsAuthors: Maria-Florina Belcan; Christopher Berlind; Steven Ehrlich; Yingyu Liang
- Cost-sensitive Multiclass Classification Risk BoundsAuthors: Bernardo Pires; Csaba Szepesvari; Mohammad Ghavamzadeh
- Active Learning for Multi-Objective OptimizationAuthors: Marcela Zuluaga; Guillaume Sergent; Andreas Krause; Markus Pueschel
- Near-optimal Batch Mode Active Learning and Adaptive Submodular OptimizationAuthors: Yuxin Chen; Andreas Krause
Social Networks
- Copy or Coincidence? A Model for Detecting Social Influence and Duplication EventsAuthors: Lisa Friedland; David Jensen; Michael Lavine
- Mixture of Mutually Exciting Processes for Viral DiffusionAuthors: Shuang-Hong Yang; Hongyuan Zha
- Dynamic Probabilistic Models for Latent Feature Propagation in Social NetworksAuthors: Creighton Heaukulani; Ghahramani Zoubin
- Modeling Information Propagation with Survival TheoryAuthors: Manuel Gomez-Rodriguez; Jure Leskovec; Bernhard Sch
- Learning Triggering Kernels for Multi-dimensional Hawkes ProcessesAuthors: Ke Zhou; Le Song; Hongyuan Zha
- Causal Estimation of Peer Influence EffectsAuthors: Edward Kao; Panos Toulis; Edoardo Airoldi; Donald Rubin
- Modeling Temporal Evolution and Multiscale Structure in NetworksAuthors: Tue Herlau; Morten M
- Scalable Optimization of Neighbor Embedding for VisualizationAuthors: Zhirong Yang; Jaakko Peltonen; Samuel Kaski
Track D: Statistical Methods
- Computation-Risk Tradeoffs for Covariance-Thresholded RegressionAuthors: Dinah Shender; John Lafferty
- Scalable Simple Random Sampling and Stratified SamplingAuthors: Xiangrui Meng
- The lasso, persistence, and cross-validationAuthors: Darren Homrighausen; Daniel McDonald
- Consistency versus Realizable H-Consistency for Multiclass ClassificationAuthors: Phil Long; Rocco Servedio
- Two-Sided Exponential Concentration Bounds for Bayes Error Rate and Shannon EntropyAuthors: Jean Honorio; Jaakkola Tommi
- Scale Invariant Conditional Dependence MeasuresAuthors: Sashank J Reddi; Barnabas Poczos
- Infinite Markov-Switching Maximum Entropy Discrimination MachinesAuthors: Sotirios Chatzis
- Distribution to Distribution Regression,Authors: Junier Oliva; Barnabas Poczos; Jeff Schneide
Track C: Matrix Factorization
- Fast Conical Hull Algorithms for Near-separable Non-negative Matrix FactorizationAuthors: Abhishek Kumar; Vikas Sindhwani; Prabhanjan Kambadur
- General Functional Matrix Factorization Using Gradient BoostingAuthors: Tianqi Chen; Hang Li; Qiang Yang; Yong Yu
- Fast Max-Margin Matrix Factorization with Data AugmentationAuthors: Minjie Xu; Jun Zhu; Bo Zhang
- Local Low-Rank Matrix Approximation,Authors: Joonseok Lee; Seungyeon Kim; Guy Lebanon; Yoram Singer
- Learning the beta-Divergence in Tweedie Compound Poisson Matrix Factorization ModelsAuthors: Umut Simsekli; Yusuf Kenan Yilmaz; Ali Taylan Cemgil
- ELLA: An Efficient Lifelong Learning AlgorithmAuthors: Paul Ruvolo; Eric Eaton
- Riemannian Similarity Learning,Authors: Li Cheng
- Multiple-Source Cross ValidationAuthors: Krzysztof Geras; Charles Sutton
Deep Learning 2
- Learning the Structure of Sum-Product NetworksAuthors: Robert Gens; Domingos Pedro
- Deep learning with COTS HPC systemsAuthors: Adam Coates; Brody Huval; Tao Wang; David Wu; Bryan Catanzaro; Ng Andrew
- Learning and Selecting Features Jointly with Point-wise Gated Boltzmann MachinesAuthors: Kihyuk Sohn; Guanyu Zhou; Chansoo Lee; Honglak Lee
- Regularization of Neural Networks using DropConnectAuthors: Li Wan; Matthew Zeiler; Sixin Zhang; Yann Le Cun; Rob Fergus
- Thurstonian Boltzmann Machines: Learning from Multiple InequalitiesAuthors: Truyen Tran; Dinh Phung; Svetha Venkatesh
- No more pesky learning ratesAuthors: Tom Schaul; Sixin Zhang; Yann LeCun
- Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision ArchitecturesAuthors: James Bergstra; Daniel Yamins; David Cox
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.
No comments:
Post a Comment