A & O Apprentissage & Optimisation Head: Mich` ele Sebag Joint INRIA project, Head: Marc Schoenauer 1 / 22
Members – 2008-2013 Permanent members ◮ Jamal Atif, MdC IUT Orsay ← 2011 ◮ Anne Auger, CR INRIA ◮ Nicolas Bred` eche, MdC Univ. Paris Sud → 2012 ◮ Philippe Caillou, MdC IUT Sceaux ◮ Marta Franova, CR CNRS ◮ Cyril Furtlehner, CR INRIA ◮ C´ ecile Germain-Renaud, Prof. UPS University CNRS INRIA ◮ Nikolaus Hansen, CR INRIA ← 2009 ◮ Yann Ollivier, CR CNRS ← 2010 Non-permanent members ◮ Marc Schoenauer, DR INRIA ◮ 14 PhDs, 4 post-docs, 3 research ◮ Mich` ele Sebag, DR CNRS ◮ Nicolas Spyratos, Prof. UPS, emeritus ← 2012 engineers ◮ Olivier Teytaud, CR INRIA Some figures Associate members ◮ 18 PhDs and 3 HdRs defended ◮ Florence d’Alch´ e-Buc, Pr. Evry ◮ Guillaume Charpiat, CR INRIA, Sophia ◮ Articles 39 / 7 ◮ Bal´ azs K´ egl, DR CNRS, LAL ◮ Conferences 110 / 188 ◮ H´ el` ene Paugam-Moisy, Pr. Lyon-2 ◮ R´ emi Peyre, MdC Nancy 2 / 22
Apprentissage & Optimisation Research goals Model, predict and control physical or artificial systems A unified perspective: ◮ Learning is an optimization problem ◮ Ill-posed optimisation requires adaptation 3 / 22
Structure Core expertise Applications ◮ Machine Learning ◮ Games and Energy management ◮ Stochastic ◮ Numerical engineering Optimization ◮ Autonomic Computing ◮ Statistical Physics ◮ Robotics Special Interest Groups ◮ Stochastic continuous optimization ◮ Optimal decision making under uncertainty ◮ Criteria design ◮ Algorithm control and parameter tuning ◮ Large scale modelling 4 / 22
SIG Stochastic continuous optimization R d �→ I Argmax F : Ω ⊂ I R Covariance-Matrix Adaptation, Evolution Strategy ◮ Invariances under monotonous transform of F and affine transf. of Ω. ◮ A particular case of Information Geometry Optimization Ollivier, Auger, Hansen, Arnold, ArXiv Transfert 100+ applications in industry OMD, EADS, Renault, Dassault, Thal` es, EZCT Cifres IFP, Renault, Thal` es (x2). 5 / 22
Stochastic continuous optimization, 2 Expensive optimization ◮ PhD Bouzarkouna ◮ PhD Loshchilov ◮ Noisy optimization 6 / 22
Stochastic continuous optimization, 3 Black-Box Optimization Benchmark Extensions to multi-objective optimization: ANR NumBBO 7 / 22
Stochastic optimization Divide and Evolve: scaling up Planning ◮ Evolutionary computation + local planner ICAPS 2010; IJCAI 2013 ◮ Winner temporal satisficing track, IPC 2011 ◮ Winner silver award Humies GECCO 2010 ◮ Coll. Thal` es, On´ era, Cril; ◮ PhD Cifre Bibai; ANR Descarwin 8 / 22
SIG Optimal Decision Making Under Uncertainty From Go to energy management ◮ STREP MASH, Citines; ANR IOMCA, Explora; ADEME Post ◮ Coll. U. Tainan, Taiwan; ILAB SME Artelys; platform Metis. 9 / 22
Optimal Decision Making Under Uncertainty, 2 Some extensions ◮ Continuous spaces (PhD Couetoux) ◮ Double progressive widening (PhD Couetoux) ◮ Multi-objective MCTS (PhD Wang) ◮ MARAB: risk-aware MAB (PhD Galichet) Applications to Machine Learning ◮ Active Learning (PhD Rolet; Digiteo 2008-2010; coll. CEA) ◮ Feature Selection (PhD Gaudel) ◮ Coll. Orange Application to Computer Science ◮ Optimization of DFT in Spiral, coll. CMU (PhD Rimmel) ◮ Cooperation control in parallel SAT Solving, coll. Microsoft 10 / 22
Optimal Decision Making Under Uncertainty, 3 Game theory Partially observable games are undecidable even in the case of finite state spaces and deterministic transitions. Results on other games ◮ MineSweeper ◮ Havannah ◮ Urban Rivals ◮ Coll. U. Tainan; USVQ; GaLaC. World Award: Chess Base 2009 11 / 22
Optimal Decision Making Under Uncertainty, 4 MineSweeper and MCTS ◮ All locations have same probability of death 1/3 ◮ Are then all moves equivalent ? 12 / 22
Optimal Decision Making Under Uncertainty, 4 MineSweeper and MCTS ◮ All locations have same probability of death 1/3 ◮ Are then all moves equivalent ? NO ! 12 / 22
Optimal Decision Making Under Uncertainty, 4 MineSweeper and MCTS ◮ All locations have same probability of death 1/3 ◮ Are then all moves equivalent ? NO ! ◮ Top, Bottom: Win with probability 2/3 12 / 22
Optimal Decision Making Under Uncertainty, 4 MineSweeper and MCTS ◮ All locations have same probability of death 1/3 ◮ Are then all moves equivalent ? NO ! ◮ Top, Bottom: Win with probability 2/3 ◮ MYOPIC approaches LOSE. 12 / 22
Optimal Decision Making Under Uncertainty, 5 Multi-armed bandits and Constraint Programming ◮ Coll. Microsoft-INRIA, KTH. ◮ Invited tutorial CP 2012 ◮ Dagstuhl 2014, Constraints, Optimization and Data (co-organization with L. de Raedt, B. O’Sullivan, P. Van Hentenryck). Zoom ◮ Bandit-based Search for Constraint Programming CP 13 13 / 22
Large scale modelling (Big data) Context: EGEE Enabling Grids for e-Science in Europe: 100,000 + CPU; 5Pb storage; 300,000 jobs/day Data acquisition ◮ Grid Observatory portal ◮ Coll. LAL, Imperial College ◮ EGI, CNRS, INRIA, Digiteo, UPS 14 / 22
Large scale modelling, 2 Autonomic Computing ◮ Job allocation & quality of service (reinforcement learning; PhD Perez) ◮ Job monitoring (data streaming; PhD Zhang) TKDE 2013 ◮ Fault detection (coll. filtering; PhD Feng) X.Z: Outstanding Award from National China Research Council for Abroad Students Zoom on Data Streaming with Affinity Propagation exemplars WEIGHTED AFFINITY PROPAGATION exemplars N subsets AFFINITY PROPAGATION n 2 → n 1+ ǫ scale invariance PhysRev 10 15 / 22
Future Scientific goals ◮ Multi-scale optimization under uncertainty ◮ Representation design, information theory and priors ◮ Tackling the underspecified (Human-Machine-Loop) Initiative ◮ Data science institute proposal @ UPSay, B. K´ egl co-PI 16 / 22
Multi-scale optimization under uncertainty Challenges ◮ Stochastic uncertainties (price, demand, weather) ◮ Large-scale problems & non-linear effects ◮ High dimension ◮ Multi-scale time horizons POST (ADEME) 17 / 22
Representation design, information theory, priors Deep learning ◮ Tiling the space vs learning features Bengio, 2012 Directions ◮ Best latent marginal (PhD Arnold) � � arg max q I E [log P ( x | h ) q D ( h )] with q ( h ) = q ( h | ˜ x ) P D (˜ x ) ˜ h x ◮ Enforcing priors (PhD Isaac, coll. CEA LIST) 18 / 22
Tackling the underspecified Reconsidering optimal decision and design ◮ Reinforcement learning: rewards are given ◮ Inverse RL: learning rewards from expert demonstrations Directions ◮ Preference-based reinforcement learning (PhD Akrour, IP SYMBRION) ◮ Open-ended evolution (PhD Montanier, IP SYMBRION) 19 / 22
UPSay & Data Science Institute The 4th paradigm: Data-driven science ◮ Initially push by industry and e.g. physics and biology ◮ International initiatives: Data to Knowledge to Action; NYU; Berkeley; Amsterdam; ... UPSay ◮ Labex DigiCosme, axis DataSense ◮ Master ML-Information & Contents with LTCI, LIX, Evry, ECP, ENSTA 20 / 22
Visibility International Committees Editorship ◮ ACM SIGEVO Exec. ◮ Editor in Chief Evolutionary Computation ◮ PPSN Steering (2002-2009), Editorial ◮ PASCAL -I, -II Steering Board Member GPEM, ◮ EGEE III Steering ASOC, TCS-C, EC ◮ Editorial Board Member Organisation, coordination MLJ, GPEM, KAIS ◮ Dagstuhl Theory of EC 08, 10 Program Committees ◮ ThRaSH Wshp (2009-now) ◮ Co-chair ECML/PKDD ◮ BBOB Wshp (2009-10-12-13) 2010 ◮ PASCAL Wshops and Challenges ◮ Major ML conf (NIPS, ◮ Grids Meet AC 09 ICML, ECML, PKDD, IEEE-ICDM) ◮ EvoDeRob, IROS’09 ◮ Major EC conf. (PPSN, ◮ LION 2012 ACM GECCO, IEEE CEC, ◮ Digiteo, DigiCosme, UPSay senate Evo*) Yann Ollivier : Bronze medal CNRS 21 / 22
Apprentissage & Optimisation THEORY LOGIMA PASCAL1 −2 (NoE) OMD1−2 SIMINOLE Simplified Models NumBBO DigiBrain TRAVESTI MACHINE LEARNING GENNETEC (Strep) Unsup. Brain IFP MASH (Frp) OPTIMISATION POST ASAP Adapt (Microsoft−INRIA) SYMBRION (IP) DEMAIN SyDiNMaLaS EvoTest (Strep) DigiBrain EGEE III (IP) Grid Observatory CSDL Citines (Strep) Modyrum DESCARWIN TIMCO (Bull) Innov’Nation IOMCA Orange Peugeot APPLICATIONS Legend: Europe ANR Region Industry 22 / 22
Recommend
More recommend
