MLSP-L2: Optimization Algorithms I |
| Session Type: Lecture |
| Time: Wednesday, 6 May, 11:30 - 13:30 |
| Location: On-Demand |
| Virtual Session: View on Virtual Platform |
| Session Chair: Simo Särkkä, Aalto University |
| MLSP-L2.1: PRIMAL-DUAL STOCHASTIC SUBGRADIENT METHOD FOR LOG-DETERMINANT OPTIMIZATION |
| Songwei Wu; Nanyang Technological University |
| Hang Yu; Nanyang Technological University |
| Justin Dauwels; Nanyang Technological University |
| MLSP-L2.2: NEURAL NETWORK TRAINING WITH APPROXIMATE LOGARITHMIC COMPUTATIONS |
| Arnab Sanyal; University of Southern California |
| Peter Beerel; University of Southern California |
| Keith Chugg; University of Southern California |
| MLSP-L2.3: AUTOMATIC AND SIMULTANEOUS ADJUSTMENT OF LEARNING RATE AND MOMENTUM FOR STOCHASTIC GRADIENT-BASED OPTIMIZATION METHODS |
| Tomer Lancewicki; eBay |
| Selcuk Kopru; eBay |
| MLSP-L2.4: A STUDY OF GENERALIZATION OF STOCHASTIC MIRROR DESCENT ALGORITHMS ON OVERPARAMETERIZED NONLINEAR MODELS |
| Navid Azizan; California Institute of Technology |
| Sahin Lale; California Institute of Technology |
| Babak Hassibi; California Institute of Technology |
| MLSP-L2.5: ON DISTRIBUTED STOCHASTIC GRADIENT DESCENT FOR NONCONVEX FUNCTIONS IN THE PRESENCE OF BYZANTINES |
| Saikiran Bulusu; Syracuse University |
| Prashant Khanduri; Syracuse University |
| Pranay Sharma; Syracuse University |
| Pramod Varshney; Syracuse University |
| MLSP-L2.6: PRECONDITIONING ADMM FOR FAST DECENTRALIZED OPTIMIZATION |
| Meng Ma; University of Minnesota |
| Georgios B. Giannakis; University of Minnesota |