Harsh Mehta
11 papers · 2019–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🏃 Academic Marathon (5) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (14)
🏃
Academic Marathon
(5)
🌉
Interdisciplinary Bridge
🐝
Cross-Pollinator
(14)
👑
Triple Crown
🧬
Topic Evolution
💎
Century Club
(11)
🔥
Unstoppable
(6)
Conferences
NIPS (4)
ICLR (2)
ICML (2)
EMNLP (1)
ICCV (1)
NAACL (1)
Top co-authors
Keywords
non-convex optimization
(3)
learning rate
(2)
stochastic optimization
(2)
vision-language navigation
(2)
neural network optimization
(2)
transfer learning
(1)
cross-modal learning
(1)
stochastic gradient descent
(1)
multimodal learning
(1)
complexity bound
(1)
information retrieval
(1)
deep learning
(1)
data augmentation
(1)
language grounding
(1)
online convex optimization
(1)
gradient descent
(1)
adaptive learning rate
(1)
hyperparameter tuning
(1)
convex optimization
(1)
online learning
(1)
Papers
The Road Less Scheduled
NIPS 2024
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion
ICML 2023
Mechanic: A Learning Rate Tuner
NIPS 2023
Long Range Language Modeling via Gated State Spaces
ICLR 2023
Transformer Memory as a Differentiable Search Index
NIPS 2022
High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails
NIPS 2021
Extreme Memorization via Scale of Initialization
ICLR 2021
Momentum Improves Normalized SGD
ICML 2020
Retouchdown: Releasing Touchdown on StreetLearn as a Public Resource for Language Grounding Tasks in Street View
EMNLP 2020
Multi-modal Discriminative Model for Vision-and-Language Navigation
NAACL 2019
Transferable Representation Learning in Vision-and-Language Navigation
ICCV 2019