HTTP/2 200
content-type: text/html; charset=utf-8
x-frame-options: DENY
vary: Sec-Fetch-Dest, Sec-Fetch-Mode, Sec-Fetch-Site
cache-control: no-cache, no-store, max-age=0, must-revalidate
pragma: no-cache
expires: Mon, 01 Jan 1990 00:00:00 GMT
date: Wed, 31 Dec 2025 05:10:45 GMT
content-security-policy: base-uri 'self';object-src 'none';report-uri /_/view/cspreport;script-src 'report-sample' 'nonce-PRNSASu_n3igkZwz5JBryA' 'unsafe-inline' 'unsafe-eval';worker-src 'self';frame-ancestors https://google-admin.corp.google.com/
cross-origin-opener-policy: unsafe-none
reporting-endpoints: default="/web-reports?jobset=prod&wcrumsspbp=false&bl=editors.sites-viewer-frontend_20251210.02_p1&app=25&clss=1&context=eJwN0GtUkwUAxvG37X0fDURkgA5SmO_UQNAmRaIwgSYboZFpuoUdIXEiXkABwUspHEXNsqOWipqXEJVETIWUsouJlZdMqcwoUBKc3LdxEbwkPR9-5_zP8_FxKR94oL9ZKHU1C9O8zMKb5LHVLAynpwVmYeBusyAWmgUv0p82C-Y7ZiGFKlvNwu80x8cipFHXMIsg-lmE5SMsQj4lx1iETMqhjTQx6JbwlBB8S_CjyLsdChPpcrsVYWTP61b00MpFPYo8uhzRq6iib_S9iov0wNqreEpHN_cqvqC5Vx4qFlKa0KfIpt6hfQphWJ-ia0Wf4gm9OEOpDKfIPKXSRNPvKZUJtMI-UcwlRUGE6EJfHY8Qf6DYML04jZxx0eJD-mf1K2I9pcMg5tCOpQZxHyVnG8RFpDhpEF1owhmDGE09QTFiH4UtjBGjaOSyGHEMrbfFiB-SJdQoJtHlL41iNX3ykUksomKqoPs9JtFOBYtixYNUr3pVbKGafnFiA-XMOCCtpb_OHpDqqKrzoFRNmtcLpQB6p-aQlErv2Q9J-XRuQZFUSccWF0mn6Up9kfQbqU8dljR0Lf6IdJPc8o9K3uTjXywNp4C3iiUdTW8-JiXQMlpJn8eXSKfo33klUhN9W1wi_UhV50ulaspIPiGtouYlJ6QO2lPaLBXSpUst0g2yRLZKSTT7QquUTDctbVItue9tk4aQ8t4AuNJJdzdU0KgKN4ylWxcH4g5lh7hjDb12wB0zyXZ4ENqppNEDZbSg2QNLqZ9OBXd6RvbEs1Q23hPnKCrME7H0-TueOEUhtV6YSNkqb6wh13hveNL2Vd7YQ_c3eMNOawsHYyM9XzMYL5DL4iFQ0aO0IXBJH4L3NWpso5RQNZqsajipvFSNb6j3shrCFTXe_cwH6-mPQh_UUM5mX6ylR3ZfKBy-2Nfji8PUsPU5tNKO6KHYQ7PjhiKJ7pT44dLffrhG9TV-aKQAux90NNPphwQ6M9sfX833x3fUXO6PDprST4MZVDZeww80aEnVoL1Cgwe0-tBwrKPJ9uGYSotfkJFFL5tkhJP3chnD6HG-DOUGGec2yaikRQdlZNK312RcoAG_yvCgHnpCxusyplAxlZLHDRmDactTGTuocJwWx-i_CC0kvRYnI7WooNZULbrIsVKLbkr4Q4u5lPjFCKRQV_kIPKE48yhMp3rLKLRQh1sAHpEcHIDR9HNhAK7Tn7YA3KYK90CcpwaPQLRStWcg_qXHXoFQegeiSgjH1ZJw_E4l8REooz5Bj37P6BHuqscUWrpTjxU0Wz0JyVSzfRIayKqMxEJyGRkJFdUER6GBzhuicIO0F6MQREsM0VhO1QXRaLoRDSflNUfjfVrnY8AHtM1owG4abDVATc7FBjwku3Iy-sh72mQMI7e32XS7fTJs5JlshJpSco1IJ22REUG0_6gRR2jCJSOiqS3LhG6Sj5swmjpKTXhEuXUmbKKPx8ZiL1XeicVVur35LmyU2HgX80j1RgN8yeVhA1S0a4wNn1JGrg2rSHPBhgCypDUiiZYUNWI56QY0IYxWPmhCHu2rbcZhqmptRjVZZ7Xg9IoWfE33t7Qg2b8NC2intQ37qS2iHd006mw7VJvsOH7SjnJapndAnuPAaMpKd-DYOgfufejA9K0O7KpxoK3OAd1LTiTNd2IBde5w4jFt-NKJvVQ7tQO_LOyA54kOqGmmVydsiZ2In9uJ76O6MGtVF2pXd-GNyi7k0ME5PQhN6cFPA3oRJfdC5dr_Zt1vVzCobvO1UF9xVqo1Rw62zkvNSs_IHJuZmmXNHJPNzZoxZn5GelqWNW1eYoguJHRcyDjdWF1I4tJx_wNFvLaw&build-label=editors.sites-viewer-frontend_20251210.02_p1&imp-sid=CLfD-vyH55EDFTy0IwAdC5cmcw&is-cached-offline=false"
document-policy: include-js-call-stacks-in-crash-reports
referrer-policy: strict-origin-when-cross-origin
server: ESF
x-xss-protection: 0
x-content-type-options: nosniff
content-encoding: gzip
Itay Evron
Itay Evron Research Scientist | Central Applied Science | Meta
I am a research scientist at the Central Applied Science team at Meta.
Previously, I finished my PhD at the Electrical Engineering department at the Technion, under supervision of Prof. Daniel Soudry . My PhD research focused on theoretical aspects of Continual Learning .
Feel free to reach out by mail: itay (@) evron.me
Are Greedy Task Orderings Better Than Random in Continual Linear Regression? Tsipory*, Levinstein*, Evron * , Kong*, Needell, and Soudry. NeurIPS 2025.
Optimal Rates in Continual Linear Regression via Increasing Regularization Levinstein*, Attia*, Schliserman*, Sherman*, Koren, Soudry, and Evron . NeurIPS 2025.
From Continual Learning to SGD and Back: Better Rates for Continual Linear Models Evron *, Levinstein*, Schliserman*, Sherman*, Koren, Soudry, and Srebro. ALT 2026 .
Provable Tempered Overfitting of Minimal Nets and Typical Nets Harel, Hoza, Vardi, Evron , Srebro, and Soudry. NeurIPS 2024.
The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting – An Analytical Model Goldfarb*, Evron *, Weinberger, Soudry, and Hand. ICLR 2024.
Continual Learning in Linear Classification on Separable Data Evron , Moroshko, Buzaglo, Khriesh, Marjieh, Srebro, and Soudry. ICML 2023 .
The Role of Codeword-to-Class Assignments in Error Correcting Codes: An Empirical Study Evron *, Onn*, Weiss , Azeroual, and Soudry. AISTATS 2023 .
How catastrophic can catastrophic forgetting be in linear regression? Evron , Moroshko, Ward, Srebro, and Soudry. COLT 20 22 .
How do infinite width bounded norm networks look in function space? Savarese, Evron , Soudry, and Srebro. COLT 2019 .
Towards Learning of Filter Level Heterogeneous Compression of Convolutional Neural Networks Zur, Baskin, Zheltonozhskii, Chmiel, Evron , Bronstein, and Mendelson. Auto ML Workshop, ICML 2019.
Efficient Loss Based Decoding on Graphs for Extreme Classification Evron , Moroshko, and Crammer. NeurIPS 2018.
2024 - Today | Research Scientist | Meta
2018 - 2019 | Research Intern | eBay
2013 - 2015 | Software Developer | Quali ltd.
2020 - 2024 | Ph.D. in Electrical Engineering | Technion
2015 - 2018 | M.Sc. in Computer Science | Technion | Magna cum Lauda
2012 - 2015 | B.Sc. in Computer Science | The College of Management | Magna cum Lauda
Introduction to Machine Learning
Project advisor in Machine Learning
Numerical Algorithms
Project advisor in Artificial Intelligence
Introduction to Artificial Intelligence
Algorithms 1
Introduction to Computer Science
