PR/CV Reading group

Please note that the schedule for the first cycle is very tentative, since there was little consensus over the type of papers that people wanted to discuss. Let's take a part of the first meeting to discuss what everyone would like to get out of these meetings.

You can find the Google Calendar for these meetings and the CoffeeTalks here

Cycle 1 (Spring 2014): Deep Learning

Recently learned deep architectures, such as convolutional neural networks, deep boltzman machines and deep belief networks, have shown large performance improvements over the state of the art on many prediction tasks. In this cycle we will investigate how these methods work and how and when to apply them in practice.

DateLocationPaperDownload
7 March 2014HB13.100Hastie et. al. - Elements of Statistical Learning: Chapter 11: Neural NetworksLink
21 March 2014HB13.100Bengio et. al - Representation Learning: A Review and New Perspectives - Sections 1-2, 5, 6.2, 7-7.2.3, 8Link
4 + 11 April 2014HB13.100Bengio et. al - Representation Learning: A Review and New Perspectives - Sections 3, 4, 10.1, 11-11.2, 12Link
2 May 2014HB13.100Krizhevsky et. al. - ImageNet Classification with Deep Convolutional
Neural Networks
Link
9 May 2014HB13.100Postponed
23 May 2014HB13.100Taigman et. al - DeepFace: Closing the Gap to Human-Level Performance in Face VerificationLink
12 June 2014HB13.100Zeiler & Fergus - Visualizing and Understanding Convolutional Networks
Also have a look at this blogpost
Link

A related CVPR tutorial (link by Wenjie).

Cycle 2 (Fall 2014): Gaussian Processes

DateLocationPaperDownload
19 September 2014HB13.100Rasmussen & Willams - Gaussian Processes for Machine Learning: Chapter 1 up to and including section 2 of Chapter 2Link
3 October 2014HB13.100Rasmussen & Willams - Gaussian Processes for Machine Learning: Chapter 2.3 up to and including section 3 of Chapter 3Link
17 October 2014HB13.100CanceledLink
31 October 2014HB13.100CanceledLink
14 November 2014HB13.100Rasmussen & Willams - Gaussian Processes for Machine Learning: Chapter 3 up to and including section 4 of Chapter 3Link
12 December 2014HB13.100Rasmussen & Willams - Gaussian Processes for Machine Learning: Chapter 4Link

Related slides (link by Andre).

Cycle 3 (Spring 2015): Graphical Models

DateLocationPaperDownload
16 January 2015HB13.100Christopher Bishop - Pattern Recognition and Machine Learning: Chapter 8 up to and including 8.3
6 February 2015HB13.100Christopher Bishop - Pattern Recognition and Machine Learning: Chapter 8: 8.4
20 February 2015HB13.100Christopher Bishop - Pattern Recognition and Machine Learning: Chapter 8: 8.4 (Again) and Dense CRF paper suggested by GorkemLink
6 March 2015HB13.100Philipp Krahenbuhl & Vladlen Koltun - Efficient Inference in Fully Connected CRFs with Gaussian Edge PotentialsLink
20 March 2015HB13.100Herbrich, Ralf; Minka, Tom; Graepel, Thore - TrueSkill: A Bayesian Skill Rating SystemLink
27 March 2015HB13.100Roweis, S. & Ghahramani, Z., 1999. A unifying review of linear gaussian models. Neural computation, 11(1995), pp.305–345. (First 15 pages)

Cycle 4 (Summer 2015): Graphical Models, Exponential Families and Variational Inference

During the summer (2015) we will be reading the monograph "Graphical Models, Exponential Families and Variational Inference" by Wainwright and Jordan.

Cycle 5 (Fall 2015): Submodularity

DateLocationPaperDownload
20 November 2015 13:00HB13.100Andreas Krause &
Daniel Golovin - Submodular Function Maximization pg. 1-9
Download
27 November 2015 13:00HB13.100Andreas Krause &
Daniel Golovin - Submodular Function Maximization pg. 10-24
Download
11 December 2015 13:00HB13.100Hoi, S.C.H. et al., 2006. Batch mode active learning and its application to medical image classification. In Proceedings of the 23rd International Conference on Machine learning. pp. 417–424Download
8 January 2016 13:00HB13.100Lin, H. & Bilmes, J., 2011. A Class of Submodular Functions for Document Summarization. Computational Linguistics, 1, pp.510–520.Download
22 January 2016 13:00HB13.100Narasimhan, M., Jojic, N. & Bilmes, J., 2005. Q-Clustering. In Advances in Neural Information Processing Systems. pp. 979–986.Download
12 February 2016 13:00HB13.100Bach, F., 2010. Structured sparsity-inducing norms through submodular functions. Advances in Neural Information Processing Systems NIPS’2010, pp.1–9.Download

Cycle 6 (Spring 2016): Learning bounds for regression and classification

DateLocationPaperDownload
26 February 2016 15:00HB13.100Mohri, Rostamizadeh & Talwalkar - Foundations of Machine Learning: Chapter 2Download
4 March 2016 13:00HB13.100Mohri, Rostamizadeh & Talwalkar - Foundations of Machine Learning: Chapter 2Download
18 March 2016 13:00HB13.100Mohri, Rostamizadeh & Talwalkar - Foundations of Machine Learning: Chapter 3Download
21 April 2016 13:00HB13.100Mohri, Rostamizadeh & Talwalkar - Foundations of Machine Learning: 3.2-3.4Download
13 May 2016 13:00HB13.100Mohri, Rostamizadeh & Talwalkar - Foundations of Machine Learning: 4.4. Margin-theory, 5.3.3. Learning Guarantees and 10.2. Generalization BoundsDownload
27 May 2016 13:00HB13.100Mohri, Rostamizadeh & Talwalkar - Foundations of Machine Learning: 11. Algorithmic StabilityDownload

List of suggested future topics

  • Markov Chain Monte Carlo methods
  • Gaussian Processes
  • Learning bounds for regression and classification
  • Manifolds and Riemannian Geometry
  • Machine Learning with Privacy Constraints
  • Big Data (as suggested by Marco)

Colloquium Slides

Thijs van Ommen - Inconsistency of Bayesian inference when the model is wrong, and how to repair it (slides)

/* */