Harsh Mehta
11 papers · 2019–2024 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (25)
π
Triple Crown
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(52)
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Machine Learning
(7)
Artificial Intelligence
(5)
Core AI Β· Artificial Intelligence
(5)
Optimization & Theory
(5)
Deep Learning
(3)
Learning Types Β· Machine Learning
(3)
Computer Vision
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Applications
(1)
Architectures
(1)
Core AI Β· Computer Vision
(1)
Learning Paradigms
(1)
Learning Types Β· Deep Learning
(1)
Models
(1)
Keywords
non-convex optimization
(3)
gradient descent
(2)
representation learning
(2)
neural network optimization
(2)
vision-language navigation
(2)
stochastic optimization
(2)
learning rate
(2)
multimodal learning
(1)
information retrieval
(1)
online learning
(1)
data augmentation
(1)
language modeling
(1)
convex optimization
(1)
cross-modal learning
(1)
stochastic gradient descent
(1)
language grounding
(1)
deep learning
(1)
transfer learning
(1)
online convex optimization
(1)
image classification
(1)
Papers
The Road Less Scheduled
NeurIPS 2024
Long Range Language Modeling via Gated State Spaces
ICLR 2023
Mechanic: A Learning Rate Tuner
NeurIPS 2023
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion
ICML 2023
Transformer Memory as a Differentiable Search Index
NeurIPS 2022
Extreme Memorization via Scale of Initialization
ICLR 2021
High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails
NeurIPS 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