Lisa_seminaires Novembre 2017

lisa_seminaires@iro.umontreal.ca

1 participants
6 discussions

[Tea Talk] Romain Laroche (MS Maluuba) Fri Dec 1 10:30AM, AA6214
by Michael Noukhovitch 01 Déc '17

01 Déc '17

This week we have a researcher from MS Maluuba, *Romain Laroche,* giving a talk on *Friday Dec 1* at* 10:30AM* in room *AA6214*. See you there, this RL talk is sure to be rewarding! Michael *KEYWORDS* policy-based RL, bootstrapping, data/computational efficiency *TITLE *Safe Policy Improvement with Baseline Bootstrapping *ABSTRACT* A common goal in Reinforcement Learning is to derive a good strategy given a limited batch of data. In this paper, we propose a new strategy to compute a safe policy, guaranteed to perform at least as well as a given baseline strategy. We advocate that the assumptions made in previous work are too strong for real world applications and propose new algorithms allowing those assumptions to be satisfied only in a subset of the state-action pairs. While significantly relaxing the assumptions, our algorithms achieve the same accuracy guarantees than the previous work, and are also much more computationally efficient. We also show that the algorithms can be adapted to model-free Reinforcement Learning. *BIO* Graduated from Ecole Polytechnique in 2001 and then from Telecom PariTech in 2003, Romain Laroche joined the dialogue team at Orange in Paris, where he defended in 2010 a corporate PhD on Reinforcement Learning for industrial dialogue systems at Université Pierre et Marie Curie (Paris VI). Romain joined Maluuba in 2016, and is now a researcher at Microsoft Research Maluuba. During the past 6 years he supervised 5 PhDs, 3 postdocs, and a dozen of undergrad interns. Counting more than 40 papers at international conferences, his interest focuses now on Reinforcement Learning. His preferred application domains are dialogue systems (still his primary real-world motivation), Atari games (for benchmarking against other algorithms), and navigation toy problems (for empirical analysis and algorithm design).

1 1

[Tea Talk] Sergey Plis (MRN) Fri Nov 24, 10:30AM, AA6214
by Michael Noukhovitch 24 Nov '17

24 Nov '17

This week we have TWO tea talks (what a treat!) Apart from Martin Arjovsky's talk on Thursday, we also have the director of machine learning at the Mind Research Network, *Sergey Plis,* giving a talk on *Friday Nov 24* at* 10:30AM* in room *AA6214*. Hope this gives you cause to come, there's lots to learn! Michael *KEYWORDS *neuroscience, brain imaging, bayesian networks, structure learning *TITLE *Causal learning in complex time series datasets *ABSTRACT* Cortical neurons form coherent functional networks that are surprisingly stable across subjects and conditions. Together these networks comprise a set of functional units of the brain. Understanding their interactions can lead to better understanding of brain’s function and dysfunction due to disruption of the interaction structure. The most common way of assessing this structure are cross-correlation matrices (usually referred to as functional connectivity) but their drawbacks make us turn to modelling interactions via the directed graph of a Bayesian network (effective connectivity). Various brain imaging modalities contain different and arguably complementary information about interactions of functional network. Our goal is to bring together multimodal information to improve effective connectivity estimates. In particular, I focus on the problem of finding a common denominator for causal structures learned from time series at different time scales. I will demonstrate 1) a general theory which explains the effects of undersampling on apparent causal structure in terms of the true structure at the causal time scale; 2) a forward algorithm that computes a graph structure at any given undersampling rate; and 3) some inverse algorithms to compute all of the candidate graphs that could have generated the given undersampled structure. Although the problem is inspired by the questions from brain imaging, all time series models that are assessing structural relations are affected by the phenomena that I will describe. This includes Dynamic Bayesian Networks on the causal learning side and such models as vector autoregressive (VAR), structured VAR, Granger causality. *BASED ON* Cook, John W., David Danks, and Sergey M. Plis. (2017) "Learning Dynamic Structure from Undersampled Data <https://www.cs.purdue.edu/homes/eb/causal-uai17/papers/7.pdf>." UAI Causality Workshop A constraint optimization approach to causal discovery from subsampled time series data <https://scholar.google.ca/scholar?oi=bibs&cluster=5464303113063724661&btnI=…> A Hyttinen, S Plis, M Järvisalo, F Eberhardt, D Danks - International Journal of Approximate Reasoning, 2017 Danks, D., & Plis, S. M. (2017). Amalgamating evidence of dynamics. Synthese. [PDF <http://www.andrew.cmu.edu/user/ddanks/papers/Amalgamation-Synthese-Prepub.p…> ] Plis, S., Danks, D., Freeman, C., & Calhoun, V. (2015). Rate-agnostic (causal) structure learning. In Advances in neural information processing systems 28 (pp. 3303-3311). La Jolla, CA: The NIPS Foundation. (First two authors contributed equally.) [PDF <http://www.andrew.cmu.edu/user/ddanks/papers/RASL-NIPS-final.pdf>] Plis, S., Danks, D., & Yang, J. (2015). Mesochronal structure learning. In M. Meila & T. Heskes (Eds.), Uncertainty in artificial intelligence 31 (UAI-2015) (pp. 702-711). Corvallis, OR: AUAI Press. (First two authors contributed equally.) [PDF <http://www.andrew.cmu.edu/user/ddanks/papers/MSL-UAI15-final.pdf>] Danks, D., & Plis, S. (2014). Learning causal structure from undersampled time series. In JMLR: Workshop and Conference Proceedings. (First two authors contributed equally.) [PDF <http://www.andrew.cmu.edu/user/ddanks/papers/DanksPlis-Final.pdf>] *BIO*Dr. Sergey Plis is a Director of Machine Learning at the Mind Research Network. His research interests lie in developing novel and applying existing techniques and approaches to analyzing large scale datasets in multimodal brain imaging and other domains. He develops tools that fall within the fields of machine learning and data science. One key goal is to take advantage of the strengths of imaging modalities and infer structure and patterns that are hard to obtain non-invasively and/or that are unavailable for direct observation. In the long term this amounts to developing methods capable of revealing mechanisms used by the brain for forming task specific transient interaction networks and their cognition-inducing interactions via multimodal fusion at features and interaction levels. Ongoing work is focused on inferring multimodal probabilistic and causal descriptions of these function-induced networks based on fusion of fast and slow imaging modalities. This includes feature estimation via deep learning-based pattern recognition and learning causal graphical models. Dr. Plis is also the R&D director at a young machine learning startup reason8.ai

1 1

[Tea Talk] Martin Arjovsky (NYU) Thr Nov 23, 10:30AM, AA6214
by Michael Noukhovitch 23 Nov '17

23 Nov '17

This week we have a former MILA intern, *Martin Arjovsky,* now at NYU giving a talk on *Thursday Nov 23* at* 10:30AM* in room *AA6214*. Be there or be probabilistically sqaure! Michael *KEYWORDS* deep learning theory, probability theory, geometry *TITLE* A few geometrical insights into unsupervised learning *ABSTRACT* This short talk will address the connections and properties of the energy (including Cramer), and Wasserstein distances, and how they connect with Maximum Mean Discrepancy. We will dive into the similarities and differences among them, and how this impacts their behaviour in different ways. Some of the results are a contextualization of old studies, and some will be presented in this talk for the first time. A recurrent theme in the talk will be the study of the geometry of the space of probability distributions, and how this might shed clarity on the behaviour of different algorithms in practice. *BIO* I'm Martin Arjovsky, I'm currently doing my PhD at New York University, and being advised by Léon Bottou. I did my undergraduate and master's in the University of Buenos Aires, Argentina (my home country). In the middle I took a year off to do internships in different places (Google, Facebook, Microsoft, and the Université de Montréal). My master's thesis advisor was Yoshua Bengio, who also advised me during my stay at UdeM. In general I'm interested in the intersection between learning and mathematics, how we can ground the different learning processes that are involved in different problems, and leverage this knowledge to develop better algorithms.

1 1

[Tea Talk] Zac Kenton (MILA) Fri Nov 17, 10:30AM, AA6214
by Michael Noukhovitch 17 Nov '17

17 Nov '17

This week we have our very own *Zac Kenton*, a visiting researcher at MILA giving a talk on *Friday Nov 17* at* 10:30AM* in room *AA6214*. I've suggested that the full title should be "Three factors influencing minima in SGD: You'll never believe #1 and #3!" See you there! Michael *KEYWORDS:* SGD, Deep Learning Theory, Generalization *TITLE* Three factors influencing minima in SGD *ABSTRACT* We focus on the importance of noise in stochastic gradient descent (SGD) based training of deep neural networks (DNNs). We develop theory that studies SGD training as a stochastic differential equation and show that its stationary distribution is related to the loss surface. Our analysis suggests that the combination of batch size, learning rate, and the variance of the true loss gradients acts as a hyper- parameter steering the behavior of SGD and determines the trade-offs between the depth and width of the minima that SGD converges to. In a nutshell, a higher ratio of learning rate to batch size leads to wider minima. We validate our theory by examining the correlation between these three factors and the final performance and sharpness of the minimum found. As a verification of our theory, we empirically demonstrate that the learning dynamics is similar between experiments with different learning rates and batch sizes in SGD if the ratio of learning rate to batch size is the same. *BIO* Zac studied Mathematics at the University of Cambridge for a bachelors and masters 2009-2013. He then completed a PhD in theoretical physics at the Centre for Research in String Theory, Queen Mary University of London, 2013- August 2017. His thesis was on string theory and early universe inflationary cosmology. In the final stages of his PhD he also worked as a data scientist at ASI Data Science, a London-based data science startup. At MILA he's been working with Stanislaw Jastrzebski, Devansh Arpit and Prof Bengio on topics around generalization in SGD.

1 1

[Tea Talk] Rosemary Ke (MILA) Nov 10 10:30AM AA6214
by Michael Noukhovitch 10 Nov '17

10 Nov '17

This week we have our very own *Rosemary Ke* giving a talk on *Friday Nov 10* at* 10:30AM* in room *AA6214*. See you there! Michael *KEYWORDS* RNN, BPTT, Attention Mechanism *TITLE *Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks *ABSTRACT* A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation. This makes BPTT both computationally impractical and biologically implausible. For this reason, full backpropagation through time is rarely used on long sequences, and truncated backpropagation through time is used as a heuristic. However, this usually leads to biased estimates of the gradient in which longer term dependencies are ignored. Addressing this issue, we propose an alternative algorithm, Sparse Attentive Backtracking, which might also be related to principles used by brains to learn long-term dependencies. Sparse Attentive Backtracking learns an attention mechanism over the hidden states of the past and selectively backpropagates through paths with high attention weights. This allows the model to learn long term dependencies while only backtracking for a small number of time steps, not just from the recent past but also from attended relevant past states.

1 1

[Tea Talk] Pierre-Yves Lablanche (AIMS-South Africa) Nov 3 10:30AM AA6214
by Michael Noukhovitch 03 Nov '17

03 Nov '17

This week we have a Post-Doc from AIMS-South Africa, *Pierre-Yves Lablanche,* giving a talk on *Nov 3* at* 10:30AM* in room *AA6214* If anyone is interested in talking with Pierre-Yves about collaborating, hearing about different datasets/challenges, or is just interested in having a 1:1 chat, email me and I'll set it up! Sorry for the late email! Michael *KEYWORDS *Astronomy/Astrophysics, Statistical ML, Big Data *TITLE *Machine Learning for Astronomy *ABSTRACT* Astronomy and astrophysics like many other scientific field is entering the big data era. Observational instruments such as the Large Synoptic Survey Telescope (LSST) and the Square Kilometre Array (SKA) will produce hundreds of petabytes of data per year supporting many scientific projects and existing analysis and processing tools will not be sufficient to tackle the upcoming “big data” challenge. As a consequence a lot of focus has been given to machine learning techniques both supervised and unsupervised over the past years. In this talk I will present a case study of galaxies identification using unsupervised learning and discuss the results evaluation as well as the method application to future astronomical data. In addition I will give insights about some of the latest machine learning technique being used and developed within the astronomical community. *BIO* Dr. Pierre-Yves Lablanche, born in Saint-Etienne in France, completed a BSc. in Physics and Chemistry at the Université Jean Monnet in Saint- Etienne in 2006 and a MSc. in Physics at the Univsersité Lyon 1 in 2008. He did his Ph.D. in astrophysics between Lyon and the European Southern Observatory (Münich, Germany) investigating the dynamics of barred galaxies via N-body simulations until 2012. The Ph.D. years were followed by two years of work as a scientific educator in a local association in Saint-Chamond (France) before volunteering to become a tutor at the African Institute for Mathematical Sciences (AIMS) in Arusha (Tanzania) in September 2014. A year later he joined the AIMS research centre in Cape Town (South Africa) where he is still working as a postdoctoral research fellow. Although his Ph.D. focused on astrophysics, Pierre-Yves nowadays develop and applies machine learning techniques in various field such as astronomy, anthropology, text analysis and infrastructure development. Aside from his research he is involved in many science outreach activities in France, Tanzania and South Africa and collaborates with the International Astronomical Union Office of Astronomy for Development on various international projects. Dr. Lablanche more specifically focuses on activities toward minorities and disabled people humbly trying to make a little difference everywhere he goes, strongly believing that “Education is the most powerful weapon which you can use to change the world” (Nelson Mandela).

1 1

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Lisa_seminaires Novembre 2017