46 citations · 304 across the 59 of their papers we have counts for
4 papers · 1 filter
Efficient Learning of Linear Separators under Bounded Noise
Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab +1
We study the learnability of linear separators in in the presence of bounded (a.k.a Massart) noise. This is a realistic generalization of the random classification noise mo…
On some provably correct cases of variational inference for topic models
Pranjal Awasthi, Andrej Risteski
Variational inference is a very efficient and popular heuristic used in various forms in the context of latent variable models. It's closely related to Expectation Maximization (EM…
Label optimal regret bounds for online local learning
Pranjal Awasthi, Moses Charikar, Kevin A. Lai +1
We resolve an open question from (Christiano, 2014b) posed in COLT'14 regarding the optimal dependency of the regret achievable for online local learning on the size of the label s…
The Hardness of Approximation of Euclidean k-means
Pranjal Awasthi, Moses Charikar, Ravishankar Krishnaswamy +1
The Euclidean -means problem is a classical problem that has been extensively studied in the theoretical computer science, machine learning and the computational geometry commun…