Meta tags:

Headings (most frequently used words):

papers, andrew, ilyas, students, selected, short, miscellanea,

Text of the page (most frequently used words):
#andrew (46), ilyas (45), and (34), aleksander (33), madry (33), blog (25), post (25), logan (24), engstrom (24), with (20), icml (16), github (15), data (15), the (14), for (14), 2024 (12), 2020 (12), 2023 (12), neurips (10), 2022 (9), part (9), shibani (9), santurkar (9), presentation (8), park (8), dimitris (8), tsipras (8), 2018 (7), learning (7), workshop (7), oral (7), iclr (7), 2025 (7), 2026 (7), about (7), adversarial (6), sarah (6), cen (6), kristian (6), georgiev (6), from (6), 2019 (6), hadi (6), salman (6), models (6), work (6), robustness (5), systems (5), slides (5), scale (5), algorithms (5), code (5), guillaume (5), leclerc (5), speaking (5), sam (4), papers (4), daskalakis (4), training (4), robust (4), attacks (4), video (4), are (4), image (4), bias (4), 2021 (4), sung (4), min (4), behavior (4), strategization (4), cmu (4), anish (3), athalye (3), machine (3), computer (3), vision (3), attribution (3), constantinos (3), examples (3), prior (3), brandon (3), tran (3), deep (3), policy (3), ashish (3), kapoor (3), transfer (3), testing (3), datamodels (3), manolis (3), zampetakis (3), alaa (3), khaddaj (3), optimizing (3), large (3), selected (3), mit (3), october (3), organizing (3), recent (3), stanford (3), research (3), email (3), talk (2), trust (2), recommender (2), documentation (2), python (2), library (2), series (2), deployment (2), tutorial (2), award (2), black (2), box (2), limited (2), does (2), firdaus (2), janoos (2), larry (2), rudolph (2), gradient (2), jacob (2), steinhardt (2), statistical (2), imagenet (2), kai (2), xiao (2), role (2), sai (2), vemprala (2), framework (2), adjusting (2), predicting (2), predictions (2), yeshwanth (2), cherapanamjeri (2), stoc (2), selection (2), saachi (2), jain (2), rethinking (2), backdoor (2), editing (2), harshay (2), shah (2), modeldiff (2), project (2), trak (2), model (2), user (2), trustworthy (2), modeling (2), future (2), via (2), metagradient (2), descent (2), martín (2), steven (2), auditing (2), show (2), all (2), advised (2), students (2), our (2), appearing (2), informs (2), tolga (2), bolukbasi (2), attrib (2), experimentally (2), giving (2), engineering (2), simons (2), seminar (2), statistics (2), assistant (2), professor (2), some (2), that (2), see (2), was (2), you (2), applying (2), programs (2), please (2), security, evaluating, understanding, logit, pairing, responsible, decision, making, poster, recording, game, theoretic, perspective, repository, pypi, package, readthedocs, homepage, ffcv, fast, forward, social, media, aspen, hopkins, isabella, struckman, luis, videgaray, notes, short, miscellanea, ieee, ghtc, 2015, chairman, winner, microfilters, harnessing, twitter, disaster, managment, joana, trindade, raul, fernandez, samuel, madden, icde, extracting, syntactic, patterns, databases, vasilis, syrgkanis, haoyang, zeng, gans, optimism, kevin, kwok, synthesizing, jessy, lin, queries, information, minutes, how, batch, normalization, help, optimization, convictions, bandits, priors, datasets, spotlight, not, bugs, they, features, learned, representations, synthesis, single, classifier, closer, look, implementation, matters, identifying, dataset, replication, classification, contextualizing, progress, benchmarks, noise, signal, backgrounds, object, recognition, adversarially, better, unadversarial, designing, objects, vibhav, vineet, pengchuan, zhang, greg, yang, quickstart, api, demos, walkthrough, 3db, debugging, mihaela, curmei, owain, evans, international, journal, epidemiology, medrxiv, previous, draft, constructing, estimates, household, transmission, sars, cov, studies, widespread, contact, tracing, estimation, standard, auction, what, makes, good, fisherman, linear, regression, under, self, eric, wong, when, aleksandar, makelov, raising, cost, malicious, powered, comparing, page, attributing, decomposing, computation, jennifer, allen, hannah, measuring, recommendation, users, adapt, shape, content, kimia, hamidieh, marzyeh, ghassemi, debiasing, d3m, improving, subgroup, roy, rinberg, shivam, garg, seth, neel, attribute, delete, unlearning, datamodel, matching, benjamin, chen, axel, feldmann, william, moses, magic, near, optimal, shivin, dass, roberto, corl, website, best, paper, datamil, selecting, robot, imitation, emmanuel, candes, tijana, zrnic, probably, approximately, correct, labels, matteo, boglioni, terrance, liu, zhiwei, canaries, privacy, alesssandro, morosini, hedi, driss, chara, podimata, automating, personalization, language, denotes, equal, contribution, tori, qiu, matan, shtepel, jiayun, jeffrey, writing, colleagues, substack, photoguard, session, td45, finding, chairing, tuesday, 15pm, kelvin, guu, ellie, pavlick, anders, soegaard, driven, platforms, sadhika, malladi, elisa, nguyen, 2nd, edition, talked, tim, scarfe, podcast, mlst, monday, 2pm, 22nd, 23rd, upcoming, mpg, amin, saberi, reading, group, called, reform, joining, carnegie, mellon, university, starting, january, really, excited, institute, llms, new, joint, ongoing, poisoning, controlconf, theory, interpretable, updates, cofounder, previously, stein, fellow, phd, student, where, fortunate, went, undergrad, majoring, math, outside, enjoy, playing, soccer, table, tennis, interests, center, around, uncovering, general, principles, describe, predict, this, usually, means, combining, tools, experiments, study, pipeline, also, like, thinking, broadly, human, consider, societal, computing, electrical, mentioning, name, your, application, currently, want, directly, brief, intro, finally, have, space, interns, feel, free, although, due, high, volume, can, guarantee, response, prospective, costis, hiddenweights, google, scholar, andrewi, edu,

Text of the page (random words):
andrew ilyas andrew ilyas andrewi at andrew cmu edu github google scholar cv i am an assistant professor at cmu and a cofounder of hiddenweights previously i was a stein fellow at stanford statistics and a phd student at mit where i was fortunate to be advised by costis daskalakis and aleksander madry i went to mit for undergrad majoring in cs and in math outside of research i enjoy playing soccer and table tennis research my research interests center around uncovering general principles that describe and predict the behavior of large scale ml systems this usually means combining statistical tools with large scale experiments to study the ml pipeline from training data to learning algorithms to deployment i also like thinking broadly about human trust in ai systems prospective students if you are applying to ph d programs consider applying to cmu s programs in societal computing electrical and computer engineering or machine learning and mentioning my name in your application if you are currently at cmu and want to work with us please email me directly with a cv and brief intro finally i have limited space for interns please feel free to email me although due to a high volume of email i can t guarantee a response selected recent updates see all see recent speaking at the stoc 2026 workshop on the role of theory in trustworthy interpretable ai giving a talk at controlconf about some ongoing data poisoning work speaking about some new joint work that i m really excited about at the simons institute future of llms workshop joining carnegie mellon university as an assistant professor starting in january 2026 co organizing a reading group called reform at stanford with amin saberi speaking at the stanford statistics seminar and simons mpg seminar on october 22nd and 23rd about upcoming work on predicting and optimizing behavior of ml models speaking at informs on experimentally testing for strategization on recommender systems monday october 21 12 45 2pm talked with tim scarfe about ml robustness and engineering on the mlst podcast co organizing with tolga bolukbasi logan engstrom sadhika malladi elisa nguyen and sam park the 2nd edition of the attrib workshop at neurips 2024 giving a tutorial on data attribution at icml 2024 with logan engstrom kristian georgiev aleksander madry and sam park our recent work on modeling and experimentally testing for user strategization on data driven platforms appearing at ec 2024 co organizing with tolga bolukbasi logan engstrom kelvin guu sam park ellie pavlick and anders soegaard the attrib workshop at neurips 2023 speaking at informs in session td45 finding and adjusting for data bias in ml co chairing with manolis zampetakis tuesday october 17 2 15pm trak modeldiff photoguard and our work on rethinking backdoor attacks appearing at icml 2023 writing about ai policy with colleagues from mit on substack students jiayun jeffrey wu co advised with steven wu matan shtepel tori qiu selected papers denotes equal contribution show all papers show selected papers automating auditing of personalization systems at scale with large language models alesssandro morosini sarah h cen andrew ilyas hedi driss aleksander madry chara podimata 2026 ec 2026 optimizing canaries for privacy auditing with metagradient descent matteo boglioni terrance liu andrew ilyas zhiwei steven wu 2025 iclr 2026 probably approximately correct labels emmanuel candes andrew ilyas tijana zrnic 2025 icml 2026 code datamil selecting data for robot imitation learning with datamodels shivin dass alaa khaddaj logan engstrom aleksander madry andrew ilyas roberto martín martín 2025 icml 2026 workshop best paper award data corl 2025 project website code magic near optimal data attribution for deep learning andrew ilyas logan engstrom 2025 optimizing ml training with metagradient descent logan engstrom andrew ilyas benjamin chen axel feldmann william moses aleksander madry 2025 attribute to delete machine unlearning via datamodel matching kristian georgiev roy rinberg sung min park shivam garg andrew ilyas aleksander madry seth neel 2024 iclr 2025 blog post data debiasing with datamodels d3m improving subgroup robustness via data selection saachi jain kimia hamidieh kristian georgiev andrew ilyas marzyeh ghassemi aleksander madry 2024 neurips 2024 blog post measuring strategization in recommendation users adapt behavior to shape future content sarah h cen andrew ilyas jennifer allen hannah li aleksander madry 2024 ec 2024 slides decomposing and editing predictions by modeling model computation harshay shah andrew ilyas aleksander madry 2024 icml 2024 blog post 1 blog post 2 github user strategization and trustworthy algorithms sarah cen andrew ilyas aleksander madry 2023 ec 2024 trak attributing model behavior at scale sung min park kristian georgiev andrew ilyas guillaume leclerc aleksander madry 2023 oral presentation icml 2023 project page blog post github modeldiff a framework for comparing learning algorithms harshay shah sung min park andrew ilyas aleksander madry 2023 icml 2023 blog post github raising the cost of malicious ai powered image editing hadi salman alaa khaddaj guillaume leclerc andrew ilyas aleksander madry 2023 oral presentation icml 2023 blog post github rethinking backdoor attacks alaa khaddaj guillaume leclerc aleksandar makelov kristian georgiev hadi salman andrew ilyas aleksander madry 2023 icml 2023 blog post github when does bias transfer in transfer learning hadi salman saachi jain andrew ilyas logan engstrom eric wong aleksander madry 2022 blog post github what makes a good fisherman linear regression under self selection bias yeshwanth cherapanamjeri constantinos daskalakis andrew ilyas manolis zampetakis 2022 stoc 2023 video estimation of standard auction models yeshwanth cherapanamjeri constantinos daskalakis andrew ilyas manolis zampetakis 2022 ec 2022 slides datamodels predicting predictions from training data andrew ilyas sung min park logan engstrom guillaume leclerc aleksander madry 2022 icml 2022 blog post 1 part 2 data constructing and adjusting estimates for household transmission of sars cov 2 from prior studies widespread testing and contact tracing data mihaela curmei andrew ilyas jacob steinhardt owain evans 2021 international journal of epidemiology medrxiv previous draft code and data 3db a framework for debugging computer vision models guillaume leclerc hadi salman andrew ilyas sai vemprala logan engstrom vibhav vineet kai xiao pengchuan zhang shibani santurkar greg yang ashish kapoor aleksander madry 2021 neurips 2022 blog post and walkthrough code and demos quickstart and api documentation unadversarial examples designing objects for robust vision hadi salman andrew ilyas logan engstrom sai vemprala aleksander madry ashish kapoor 2020 neurips 2021 blog post github do adversarially robust imagenet models transfer better hadi salman andrew ilyas logan engstrom ashish kapoor aleksander madry 2020 oral presentation neurips 2020 blog post code and models noise or signal the role of image backgrounds in object recognition kai xiao logan engstrom andrew ilyas aleksander madry 2020 iclr 2021 blog post from imagenet to image classification contextualizing progress on benchmarks dimitris tsipras shibani santurkar logan engstrom andrew ilyas aleksander madry 2020 icml 2020 blog post identifying statistical bias in dataset replication logan engstrom andrew ilyas shibani santurkar dimitris tsipras jacob steinhardt aleksander madry 2020 icml 2020 blog post implementation matters in deep policy gradient algorithms logan engstrom andrew ilyas shibani santurkar dimitris tsipras firdaus janoos larry rudolph aleksander madry 2020 oral presentation iclr 2020 slides and video a closer look at deep policy gradient algorithms andrew ilyas logan engstrom shibani santurkar dimitris tsipras firdaus janoos larry rudolph aleksander madry 2020 oral presentation iclr 2020 slides and video image synthesis with a single robust classifier shibani santurkar dimitris tsipras brandon tran andrew ilyas logan engstrom aleksander madry 2019 neurips 2019 blog post github adversarial robustness as a prior for learned representations logan engstrom andrew ilyas shibani santurkar dimitris tsipras brandon tran aleksander madry 2019 blog post github adversarial examples are not bugs they are features andrew ilyas shibani santurkar dimitris tsipras logan engstrom brandon tran aleksander madry 2019 spotlight presentation neurips 2019 blog post datasets prior convictions black box adversarial attacks with bandits and priors andrew ilyas logan engstrom aleksander madry iclr 2019 github how does batch normalization help optimization shibani santurkar dimitris tsipras andrew ilyas aleksander madry oral presentation neurips 2018 blog post video 3 minutes black box adversarial attacks with limited queries and information andrew ilyas logan engstrom anish athalye jessy lin icml 2018 blog post 1 blog post 2 github synthesizing robust adversarial examples anish athalye logan engstrom andrew ilyas kevin kwok icml 2018 blog post training gans with optimism constantinos daskalakis andrew ilyas vasilis syrgkanis haoyang zeng iclr 2018 github extracting syntactic patterns from databases andrew ilyas joana m f da trindade raul c fernandez samuel madden icde 2018 github microfilters harnessing twitter for disaster managment andrew ilyas chairman s award winner ieee ghtc 2015 short papers miscellanea data attribution at scale andrew ilyas logan engstrom kristian georgiev aleksander madry sam park icml 2024 tutorial notes slides on ai deployment blog post series sarah cen aspen hopkins andrew ilyas aleksander madry isabella struckman luis videgaray part 1 part 2 part 3 part 4 social media blog post series sarah cen andrew ilyas aleksander madry part 1 part 2 part 3 part 4 ffcv fast forward computer vision python library homepage the robustness python library github repository pypi package documentation on readthedocs a game theoretic perspective on trust in recommender systems sarah cen andrew ilyas aleksander madry 2022 talk recording poster oral presentation icml workshop on responsible decision making 2022 evaluating and understanding the robustness of adversarial logit pairing logan engstrom andrew ilyas anish athalye 2018 neurips security in machine learning workshop 2018