SMiLe CLiNiC Reading Group

This is a seminar/reading group focused on recent trends as well as basic concepts in machine learning. Each week one of our group members will present a paper from venues including conferences such as NIPS, ICML, ICCV, CVPR, and journals such as TPAMI, JMLR, IJCV. The seminar is open to all staff from the University of Sussex. Researchers from other groups of University of Sussex are welcome to attend or present at this seminar.

Organizer: SMiLe CLiNiC

Time and Location - ** please note new time as of February 2018 **

  • Friday 16:00-17:00,  Future Technologies Lab, Ground Floor, Chichester 1
  • Mode of Presentation

  • 2x Whiteboards plus colourful markers
  • Schedule

  • Feb. 9, 2018, 16:00-17:00 -- Thomas Kehrenberg
    Scott Lundberg and Su-In Lee, A Unified Approach to Interpreting Model Predictions

  • Past Sessions

  • Jan. 18, 2018, 14:00-15:00 -- Zexun Chen
    Edwin V Bonilla et al, Generic Inference in Latent Gaussian Process Models

  • Jan. 11, 2018, 14:00-15:00 -- Abetharan Antony
    David Silver et al, Mastering the game of Go without human knowledge , Nature, 2017

  • Dec. 14, 2017, 14:00-15:00 -- Luca Giacomoni
    Volodymyr Mnih et al, Human-level control through deep reinforcement learning Nature, 2015

  • Nov. 30, 2017, 14:00-15:00 -- Chris Inskip
    Afshin Rahimi et al, Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks EMNLP, 2017

  • Nov. 16, 2017, 14:00-15:00 -- David Spence
    Yaroslav Ganin et al, Domain-Adversarial Training of Neural Networks JMLR, 2016

  • Nov. 2, 2017, 14:00-15:00 -- Bradley Butcher
    Francesco Orabona and Tatiana Tomassi Training Deep Networks without Learning Rates Through Coin Betting arXiv preprint, 2017

  • Oct. 19, 2017, 14:00-15:00 -- Oliver Thomas
    Weiyang Liu et al, Iterative Machine Teaching. ICML, 2017.

  • Mar. 30, 2017, 12:00-13:00 -- David Spence - please note: will be held in CALPS lab
    Discussing PhD work: Quantification under dataset shift (joint talk with NLP group)

  • Friday Mar. 24, 2017, 10:00-11:00 -- Richard Frost - please note: change of time and day!
    David Silver et al, Mastering the game of Go with deep neural networks and tree search. Nature, 2016 (Part 1 of 2)

  • Mar. 16, 2017, 12:00-13:00 -- David Spence
    Judy Hoffman, Brian Kulis, Trevor Darrell and Kate Saenko Discovering latent domains for multisource domain adaptation. ECCV, 2012

  • Mar. 9, 2017, 12:00-13:00 -- David Spence
    Judy Hoffman, Brian Kulis, Trevor Darrell and Kate Saenko Discovering latent domains for multisource domain adaptation. ECCV, 2012

  • Mar. 2, 2017, 12:00-13:00 -- Luca Giacomoni
    Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction. MIT Press. (Part 2 of 2)

  • Feb. 23, 2017, 12:00-13:00 -- Luca Giacomoni
    Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction. MIT Press. (Part 1 of 2)

  • Jan. 25, 2017 -- Oliver Thomas
    Richard Zemel, Yu Wu, Kevin Swersky, Toniann Pitassi, and Cynthia Dwork, Learning Fair Representations. ICML, 2013.

  • Jan. 10, 2017, 12:00-13:00 -- David Spence
    Book chapter: Arthur Gretton, Alex Smole, Jiayuan Huang, Marcel Schmittfull, Karsten Borgwardt, Bernhard Schölkopf, Covariate Shift by Kernel Mean Matching.

  • Dec. 14, 2016 -- Pietro Galliani
    Paper: Chiyuan Zhang, Samy Bengio, Boritz Hardt, Benjamin Recht, Oriol Vinyals, Understanding Deep Thinking Requires Rethinking Generalization. arXiv preprint.

  • Dec. 1, 2016 -- Joseph Taylor
    Paper: Daniel Hernandez-Lobato, Viktoriia Sharmanska, Kristian Kersting, Christoph H. Lampert, Novi Quadrianto Mind the Nuisance: Gaussian Process Classification using Privileged Noise. NIPS, 2014.

  • Nov. 24, 2016 -- Nick Jarzembowski
    Paper: Anoop Korattikara, Vivek Rathod, Kevin Murphy, Max Welling Bayesian Dark Knowledge. NIPS, 2015.

  • Nov. 3, 2016 -- Pietro Galliani
    Paper: Tommi Jaakkola, Marina Meila, and Tony Jebara, Maximum Entropy Discrimination. NIPS, 1999.

  • Oct. 27, 2016 -- David Spence
    Paper: Amos J Storkey, When Training and Test Sets are Different: Characterising Learning Transfer. Dataset shift in machine learning, 2009.

  • Oct. 20, 2016 -- Luca Giacomoni
    Paper: Eric Brochu, Vlad M. Cora, Nando de Freitas, A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning. arXiv, 2010.

  • Oct. 13, 2016 -- Oliver Thomas (with Joe Taylor)
    Paper: Vladimir Vapnik and Rauf Izmailov, Learning Using Privileged Information: Similarity Control and Knowledge Transfer. JMLR, 2015.

  • Oct. 6, 2016 -- Richard Frost
    Paper: Novi Quadrianto, Alex J. Smola, Tiberio S. Caetano and Quoc V. Le, Estimating Labels from Label Proportions. JMLR, 2009.

  • Aug. 18, 2016 -- Pietro Galliani
    Paper: Geoffrey Hinton and Ruslan Salakhutdinov, Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes. NIPS, 2007.

  • Aug. 11, 2016 -- David Spence
    Paper: Orsini et al, Quantifying randomness in real networks. Nature Communications, 2015.

  • Aug. 4, 2016 -- Joe Taylor
    Paper: David Isele, Eric Eaton and Mohammad Rostami, Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning, IJCAI 2016.

  • Jul. 29, 2016 -- Novi Quadrianto
    Paper: Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna P. Gummadi, Learning Fair Classifiers, arXiv 2016.

  • Jun. 23, 2016 -- Pietro Galliani
    Paper: Matthew Richardson and Pedro Domingos, Markov Logic Networks, Machine Learning Journal 2005.

  • Jun. 16, 2016 -- Viktoriia Sharmanska
    Papers: Kiapour et al, Hipster Wars: Discovering Elements of Fashion Style, ECCV 2014; Parikh and Grauman, Relative Attributes, ICCV 2011; Herbrich et al, TrueSkill: A Bayesian Rating System, NIPS 2007.

  • Jun. 9, 2016 -- David Spence
    Paper: Gao, Wei, From classification to quantification in tweet sentiment analysis. Social Network Analysis and Mining, 2016.

  • Apr. 28, 2016 -- Joe Taylor
    Paper: Caruana, Rich and de Sa, Virginia R., Benefitting from the Variables that Variable Selection Discards. Journal of Machine Learning Research (JMLR), Vol. 3, March 2003, pp.1245-1264.

  • Apr. 14, 2016 -- Novi Quadrianto
    Paper: A. Defazio, F. Bach, and S. Lacoste-Julien, SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives. NIPS 2014.

  • Mar. 10, 2016 -- Pietro Galliani
    Paper: I. Murray, R.P. Adams, and D.J.C. MacKay, Elliptical Slice Sampling. AISTATS 2010.

  • Feb. 25, 2016 -- Viktoriia Sharmanska
    Paper: Z. Yang, M. Moczulski, M. Denil, N. de Freitas, A. Smola, L. Song, and Z. Wang, Deep Fried Convnets. ICCV, 2015.

  • Jan. 27, 2016 -- David Spence
    Paper: Marco Saerens, Patrice Latinne, and Christine Decaestecker, Adjusting the Outputs of a Classifier to New a Priori Probabilities: A Simple Procedure. Neural computation 14.1 (2002): 21-41.

  • Jan. 13, 2016 -- Joe Taylor
    Paper: David Lopez-Paz, Léon Bottou, Bernhard Schölkopf and Vladimir Vapnik, Unifying distillation and privileged information, arXiv preprint arXiv:1511.03643 (2015)

  • Dec. 16, 2015 -- Viktoriia Sharmanska (Viktoriia's notes)
    Paper: Jimmy Ba and Rich Caruana, Do deep nets really need to be deep? Advances in Neural Information Processing Systems, 2014.
    Related Paper: Geoffrey Hinton, Oriol Vinyals, and Jeff Dean, Distilling the knowledge in a neural network, arXiv preprint arXiv:1503.02531 (2015).

  • Dec. 9, 2015 --
    Paper: Shai Shalev-Shwartz, Yoram Singer and Nathan Srebro. Pegasos: Primal estimated sub-gradient solver for svm. Mathematical programming 127.1 (2011): 3-30.

  • Dec. 2, 2015 -- David Spence
    Paper: Thorsten Joachims, A support vector method for multivariate performance measures. ICML '05 Proceedings, 2005.

  • Nov. 25, 2015 -- Pietro Galliani
    Paper: Yoshua Bengio, Olivier Delalleau, and Nicolas Le Roux. The curse of highly variable functions for local kernel machines. Advances in neural information processing systems. 2005.

  • Nov. 18, 2015 -- Roland Davis
    Paper: Kenton Murray and David Chiang. Auto-Sizing Neural Networks: With Applications to n-gram Language Models. arXiv preprint, 2015.

  • Nov. 10, 2015 -- David Spence
    Paper: Saikat Guha, Rajeev Rastogi and Kyuseok Shim. ROCK: A robust clustering algorithm for categorical attributes. Data Engineering, 1999.
    Background / counter-point: Carlos Ordonez, Clustering binary data streams with K-means. Proceedings of the 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery, 2003.

  • Nov. 3, 2015 -- Pietro Galliani
    Paper: Rajesh Ranganath, Sean Gerrish, and David M. Blei. Black Box Variational Inference. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, 2014.

  • Oct. 28, 2015 -- Joe Taylor
    Paper: Vladimir Vapnik and Akshay Vashist. A new learning paradigm: Learning using privileged information. Neural Networks, 2009

  • Oct. 21, 2015 -- Novi Quadrianto
    Paper: Jonathan S. Yedidia, William T. Freeman, Yair Weiss. Understanding Belief Propagation and its Generalizations. Technical Report, 2001

  • Oct. 14, 2015 -- Viktoriia Sharmanska
    Paper: Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton. ImageNet Classification with Deep Convolutional Neural Networks. NIPS, 2012

  • Oct. 7, 2015 -- David Spence
    Paper: Tom Fawcett and Peter A. Flach. A response to Webb and Ting's on the application of ROC analysis to predict classification performance under varying class distributions. Machine Learning, 2005

  • Sep. 29, 2015 -- David Spence
    Paper: Jose Barranquero, Jorge Diez, Juan Jose del Coz. Quantification-oriented learning based on reliable classifiers. Pattern Recognition, 2015

  • Sep. 22, 2015 -- Pietro Galliani (contd.)
    Paper: Jun Zhu, Ning Chen, Eric P. Xing. Bayesian Inference with Posterior Regularization and applications to Infinite Latent SVMs. JMLR, 2014

  • Sep. 15, 2015 -- Pietro Galliani
    Paper: Jun Zhu, Ning Chen, Eric P. Xing. Bayesian Inference with Posterior Regularization and applications to Infinite Latent SVMs. JMLR, 2014

  • Sep. 8, 2015 -- Joe Taylor
    Paper: Ga Wu, Scott Sanner, Rodrigo F.S.C. Oliveira. Bayesian Model Averaging Naive Bayes (BMA-NB): Averaging over an Exponential Number of Feature Models in Linear Time. AAAI, 2015.