Kush Bhatia
21 papers · 2015–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Interdisciplinary Bridge π Cross-Pollinator (13) π Conference Polyglot (6) π Academic Marathon (9) π Renaissance Researcher (7)
πΊοΈ
Taxonomy Completionist
(41)
π§
Keyword Pioneer
π
Conference Polyglot
(6)
π
Keyword Champion
π
Century Club
(21)
π
Trend Setter
ποΈ
Keyword Collector
(94)
β‘
Prolific Year
(7)
Conferences
NIPS (11)
ICLR (4)
AISTATS (2)
ICML (2)
COLT (1)
JMLR (1)
Top co-authors
Keywords
robust regression
(3)
regret bound
(3)
convergence rate
(2)
policy optimization
(2)
policy regret
(2)
consistent estimation
(2)
derivative-free optimization
(2)
language model
(2)
hard thresholding
(2)
language model training
(1)
in-context learning
(1)
preference learning
(1)
sample efficiency
(1)
ridge regression
(1)
stochastic optimization
(1)
function approximation
(1)
instruction tuning
(1)
game theory
(1)
reinforcement learning
(1)
minimax optimization
(1)
Papers
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry
ICLR 2024
Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws
AISTATS 2023
Ask Me Anything: A simple strategy for prompting language models
ICLR 2023
On the Sensitivity of Reward Inference to Misspecified Human Models
ICLR 2023
Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification
NIPS 2023
Skill-it! A data-driven skills framework for understanding and training language models
NIPS 2023
A case for reframing automated medical image classification as segmentation
NIPS 2023
TART: A plug-and-play Transformer module for task-agnostic reasoning
NIPS 2023
Congested Bandits: Optimal Routing via Short-term Resets
ICML 2022
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models
ICLR 2022
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
JMLR 2020
Preference learning along multiple criteria: A game-theoretic perspective
NIPS 2020
Online learning with dynamics: A minimax perspective
NIPS 2020
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction
ICML 2019
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
AISTATS 2019
Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression
COLT 2019
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network
NIPS 2018
Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation
NIPS 2018
Consistent Robust Regression
NIPS 2017
Sparse Local Embeddings for Extreme Multi-label Classification
NIPS 2015
Robust Regression via Hard Thresholding
NIPS 2015