125 citations · 272 across the 13 of their papers we have counts for
9 papers · 1 filter
Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization
Aadirupa Saha, Nagarajan Natarajan, Praneeth Netrapalli +1
We study online learning with bandit feedback (i.e. learner has access to only zeroth-order oracle) where cost/reward functions $\f_t$ admit a "pseudo-1d" structure, i.e. $\f_t(\w)…
Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
Ajaykrishna Karthikeyan, Naman Jain, Nagarajan Natarajan +1
Decision trees provide a rich family of highly non-linear but efficient models, due to which they continue to be the go-to family of predictive models by practitioners across domai…
Programming by Rewards
Nagarajan Natarajan, Ajaykrishna Karthikeyan, Prateek Jain +4
We formalize and study ``programming by rewards'' (PBR), a new approach for specifying and synthesizing subroutines for optimizing some quantitative metric such as performance, res…
On Scaling Data-Driven Loop Invariant Inference
Sahil Bhatia, Saswat Padhi, Nagarajan Natarajan +2
Automated synthesis of inductive invariants is an important problem in software verification. Once all the invariants have been specified, software verification reduces to checking…
Leveraging Distributional Semantics for Multi-Label Learning
Rahul Wadbude, Vivek Gupta, Piyush Rai +3
We present a novel and scalable label embedding framework for large-scale multi-label learning a.k.a ExMLDS (Extreme Multi-Label Learning using Distributional Semantics). Our appro…
Regret Bounds for Non-decomposable Metrics with Missing Labels
Prateek Jain, Nagarajan Natarajan
We consider the problem of recommending relevant labels (items) for a given data point (user). In particular, we are interested in the practically important setting where the evalu…