Mahesh Chandra Mukkamala
4 papers · 2017–2019 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (15) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (10)
π£
Hot Topic Early Bird
Conferences
ICML (2)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
non-convex optimization
(1)
matrix factorization
(1)
online convex optimization
(1)
logarithmic regret
(1)
alternating minimization
(1)
regret bound
(1)
deep neural network
(1)
strongly convex function
(1)
adaptive gradient method
(1)
activation function
(1)
feedforward network
(1)
network width
(1)
neural network
(1)
decision region
(1)
adversarial manipulation
(1)
inertial method
(1)
bregman proximal gradient
(1)
Papers
Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms
NIPS 2019
On the loss landscape of a class of deep neural networks with no bad local valleys
ICLR 2019
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions
ICML 2018
Variants of RMSProp and Adagrad with Logarithmic Regret Bounds
ICML 2017