--- title: "Sashank Jakkam Reddi · Google — author profile and papers" description: "Sashank Jakkam Reddi, Google: 2 papers on Elamur Research (2019), h-index 30 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/sashank-jakkam-reddi/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/sashank-jakkam-reddi/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Sashank Jakkam Reddi # Sashank Jakkam Reddi Sashank Jakkam Reddi has 2 papers in our library, in 2019; often with [Sanjiv Kumar](https://md.research.elamur.ai/free/en/authors/sanjiv-kumar/), [Ankit Singh Rawat](https://md.research.elamur.ai/free/en/authors/ankit-singh-rawat/), [Satyen Kale](https://md.research.elamur.ai/free/en/authors/satyen-kale/). 2 papers in our library · 2019 [OpenAlex](https://openalex.org/A5082314161) · [**h-index 30**](https://openalex.org/authors/A5082314161) · [83 works](https://openalex.org/works?filter=author.id:A5082314161) · [4,952 citations](https://openalex.org/works?filter=author.id:A5082314161&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/sashank-jakkam-reddi/#papers) · [🔗 Cited 221 times in our library](https://md.research.elamur.ai/free/en/authors/sashank-jakkam-reddi/cited-by/) · [4 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #1841](https://md.research.elamur.ai/free/en/paper-stars/page/19/#star-1841) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Sashank+Jakkam+Reddi) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Sashank+Jakkam+Reddi) · [dblp](https://dblp.org/search?q=Sashank+Jakkam+Reddi) · [ACL Anthology](https://aclanthology.org/search/?q=Sashank+Jakkam+Reddi) ## Affiliations [🏢**Google** Mountain View · United States 2018–2025 · 36 papers*current*](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2012–2022 · 21 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) · [Numerical Analysis · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/numerical-analysis/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) ## Works by year ### 2010s [**2019** 2 papers](https://md.research.elamur.ai/free/en/authors/sashank-jakkam-reddi/year/2019/) ## Papers The most cited first (OpenAlex and our library). 1. **[On the Convergence of Adam and Beyond](https://md.research.elamur.ai/free/en/papers/reddi-2019-convergence-adam/)** *(2019 · 1,598 citations)* Adaptive optimizers such as RMSProp, Adam, AdaDelta and NAdam scale each gradient coordinate by the root of an exponential moving average of past squared gradients. 2. **[Are Transformers universal approximators of sequence-to-sequence functions?](https://md.research.elamur.ai/free/en/papers/yun-2019-transformers-universal-approximators-sequence-sequence/)** *(2019 · 97 citations)* Transformers are widely used for NLP, but it has been unclear which sequence-to-sequence mappings they can actually represent. ## All works 6 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them. 1. [**On the Convergence of Adam and Beyond arXiv:1904.09237**Sashank J. Reddi, Satyen Kale, Sanjiv Kumar*2019 · 1,598 citations*](https://md.research.elamur.ai/free/en/papers/reddi-2019-convergence-adam/) 2. **[On the Decreasing Power of Kernel and Distance Based Nonparametric Hypothesis Tests in High Dimensions ↗](https://doi.org/10.1609/aaai.v29i1.9692) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Aaditya Ramdas et al.*2015 · 115 citations* 3. [**Are Transformers universal approximators of sequence-to-sequence functions? arXiv:1912.10077**Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, et al.*2019 · 97 citations*](https://md.research.elamur.ai/free/en/papers/yun-2019-transformers-universal-approximators-sequence-sequence/) 4. **[Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization ↗](https://openalex.org/W2556623528) neural information processing systems · no summary yet**Sashank Jakkam Reddi et al.*2016 · 96 citations* 5. **[A Generic Approach for Escaping Saddle points ↗](https://arxiv.org/abs/1709.01434) arXiv (Cornell University) · no summary yet**Sashank Jakkam Reddi et al.*2017 · 52 citations* 6. **[Reasoning with Latent Thoughts: On the Power of Looped Transformers ↗](https://arxiv.org/abs/2502.17416) arXiv:2502.17416 · no summary yet**Nikunj Saunshi et al.*2025 · 44 citations* ## Co-authors here 3 co-authors with a page, the most papers together first. - [Sanjiv Kumar](https://md.research.elamur.ai/free/en/authors/sanjiv-kumar/) ×2 - [Ankit Singh Rawat](https://md.research.elamur.ai/free/en/authors/ankit-singh-rawat/) - [Satyen Kale](https://md.research.elamur.ai/free/en/authors/satyen-kale/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - Proceedings of the AAAI Conference on Artificial Intelligence - neural information processing systems ## Cited by Papers of our library cite their works 221 times (of the 149,439 papers whose bibliographies we read); [33 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/sashank-jakkam-reddi/cited-by/). Updated 2 November 2026