Arnaud LEGRAND – POLARIS

Articles posted by Arnaud LEGRAND

DATAMOVE/POLARIS BBQ 2019

Arnaud LEGRAND 2019/06/14 2019/06/14News

Super barbecue avec toutes les familles, les nouveaux, les anciens, …

Continue reading

POLARIS Bootcamp (May 2019)

Arnaud LEGRAND 2019/05/24 2019/06/14News

Internal use: the pad where we took notes on the organization. Les photos Long talks:

Arnaud Legrand: Introduction to Bayesian sampling (sources)
Bary Pradelski: Preferences, Utilities and Identity Economics
Nicolas Gast: Bandits and online …
Continue reading

News
- DATAMOVE/POLARIS BBQ 2019 2019/06/14
- POLARIS Bootcamp (May 2019) 2019/05/24
- slides of Andras Gyorgy 2016/01/15
- kickoff meeting on Feb. 11 2016/01/13
Next seminars
- 2:00 pm – 3:00 pm, September 19, 2019 – Some theory on Bayesian neural networks by Julyan Arbel (Mistis, Grenoble)
- 2:00 pm – 3:00 pm, November 14, 2019 – Paul Duetting
- 2:00 pm – 4:00 pm, December 12, 2019 – Soutenance de These de Stephan Plassart

September 2019
M	T	W	T	F	S	S
						1
2	3	4	5	6	7	8
9	10	11	12 Partially Observable Markov Decision Processes with Finite Memory, by Bruno Ziliotto (CNRS, Paris) September 12, 2019 2:00 pm – 3:00 pm Bâtiment IMAG (406) Saint-Martin-d'Hères, 38400 France Map (joint work with Krishnendu Chatterjee and Raimundo Saona (IST Austria)) A Partially Observable Markov Decision Process (POMDP) is a discrete-time repeated decision-problem where at each period, the stage payoff depends both on the stage action and on the current state of the world. The state evolves stochastically from one stage to the other. The decision-maker does not know the state, but receives a stream of signals about it. One example is an investor, that does not know exactly the state of the economy, but learns it while taking investment decisions. We consider a long interaction, and prove that the decision-maker has approximately optimal strategies that have finite memory, and thus can be implemented by a computer. Read more	13	14	15
16	17	18	19 Some theory on Bayesian neural networks by Julyan Arbel (Mistis, Grenoble) September 19, 2019 2:00 pm – 3:00 pm Bâtiment IMAG (406) Saint-Martin-d'Hères, 38400 France Map In this talk, we first present seminal works at the basis of the theory of Bayesian neural networks. These include Radford Neal result in the 90s regarding the connexion between Gaussian processes and wide neural networks, and the recent developments of this result to deep neural networks. In a second part, we focus on understanding priors in Bayesian neural networks at the unit level. More specifically, we investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities. We establish that the induced prior distribution on the units before and after activation becomes increasingly heavy-tailed with the depth of the layer. Read more	20	21	22
23	24	25	26	27	28	29
30

Meta