Devansh Arpit

2.2k citations
13 papers · 488 indexed · 1 hit paper · h-index 8

Impact in

    • Advanced Neural Network Applications
    • Machine Learning and Data Classification
    • Domain Adaptation and Few-Shot Learning
    • Adversarial Robustness in Machine Learning
    • Machine Learning and Algorithms
    • Anomaly Detection Techniques and Applications
    • Topic Modeling
    • Neural Networks and Applications

Papers in

    • Stochastic Gradient Optimization Techniques 6
    • Adversarial Robustness in Machine Learning 3
    • Neural Networks and Applications 2
    • Domain Adaptation and Few-Shot Learning 2
    • Machine Learning and ELM 1
    • Model Reduction and Neural Networks 3
Journals
International Conference on Learning Representations (1 paper)Jagiellonian University Repository (Jagiellonian University) (1 paper)arXiv (Cornell University) (6 papers)PolyPublie (École Polytechnique de Montréal) (1 paper)

In The Last Decade

Devansh Arpit

12 papers receiving 474 citations

Hit Papers

A closer look at memorization in deep networks 2017 · 344 citations
3442017202620202023100200300

Peers

Devansh Arpit
Comparison fields: 5 of 77
  • Computer Vision and Pattern Recognition 219
  • Artificial Intelligence 336
  • Statistical and Nonlinear Physics 38
  • Signal Processing 32
  • Computer Graphics and Computer-Aided Design 8
Replace Ilya Tolstikhin with:
Ilya Tolstikhin Germany
Langming Liu China
Zengke Zhang China
Predrag Neskovic United States
Muhammad Asif Khan Pakistan
Xiaochun Wang China
Sanjiv Kumar United States
Haojie Lin China
Xiaoqiang Yan China
Li Guo China
Devansh Arpit relative to Ilya Tolstikhin Germany Ilya Tolstikhin's profile →
Citations per field
00.5×1.5×2.1×
Ilya Tolstikhin · 1×
Citations per year

Countries citing papers authored by Devansh Arpit

Since Specialization
Citations

This map shows the geographic impact of Devansh Arpit's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Devansh Arpit with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Devansh Arpit more than expected).

Fields of papers citing papers by Devansh Arpit

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Devansh Arpit. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Devansh Arpit. The network helps show where Devansh Arpit may publish in the future.

Co-authors

The 25 scholars most cited alongside Devansh Arpit, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Devansh Arpit Line = papers co-authored together Devansh Arpit links everyone, so they are left out of the graph.

All Works

13 of 13 papers shown
#Work
1
A closer look at memorization in deep networks
Hit paper breakdown →
2017344
2 201850
3
Deep Nets Don't Learn via Memorization
201723
4
On the Spectral Bias of Deep Neural Networks
201818
5 201715
6 201111
7 20188
8 20137
9 20204
10
Finding Flatter Minima with SGD
20183
11 20203
12
Joint Training of Deep Auto-Encoders
20142
13 20220

About Devansh Arpit

Devansh Arpit is a scholar working on Artificial Intelligence, Statistical and Nonlinear Physics, Computer Vision and Pattern Recognition, Signal Processing and Safety Research, having authored 13 papers that have together received 488 indexed citations. Recurring topics across this work include Stochastic Gradient Optimization Techniques (6 papers), Model Reduction and Neural Networks (3 papers), Adversarial Robustness in Machine Learning (3 papers), Neural Networks and Applications (2 papers), Generative Adversarial Networks and Image Synthesis (2 papers), Advanced Neural Network Applications (2 papers), Domain Adaptation and Few-Shot Learning (2 papers) and Machine Learning and ELM (1 paper). The work is most often cited by research in Computer Vision and Pattern Recognition (219 citations), Artificial Intelligence (336 citations), Statistical and Nonlinear Physics (38 citations), Signal Processing (32 citations) and Computer Graphics and Computer-Aided Design (8 citations). Devansh Arpit has collaborated with scholars based in United States, Canada and Germany. Frequent co-authors include Aaron Courville, Yoshua Bengio, Stanisław Jastrzȩbski, Emmanuel Bengio, Tegan Maharaj, David Krueger, Asja Fischer, Maxinder S Kanwal, Nicolas Ballas and Simon Lacoste-Julien. Their work appears in journals such as International Conference on Learning Representations, Jagiellonian University Repository (Jagiellonian University), arXiv (Cornell University) and PolyPublie (École Polytechnique de Montréal).

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026