Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers.
Together, our results show that a broad category of what we term GRW approaches are not able to achieve distributionally robust generalization.
To learn such randomized classifiers, we propose the Boosted CVaR Classification framework which is motivated by a direct relationship between CVaR and a classical boosting algorithm called LPBoost.
Beyond achieving high performance across many vision tasks, multimodal models are expected to be robust to single-source faults due to the availability of redundant information between modalities.
We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end.
In this work, we instead show that it is possible to craft (universal) adversarial perturbations in the black-box setting by querying a sequence of different images only once.
1 code implementation • 13 Aug 2020 • Lars A. Bratholm, Will Gerrard, Brandon Anderson, Shaojie Bai, Sunghwan Choi, Lam Dang, Pavel Hanchar, Addison Howard, Guillaume Huard, Sanghoon Kim, Zico Kolter, Risi Kondor, Mordechai Kornbluth, Youhan Lee, Youngsoo Lee, Jonathan P. Mailoa, Thanh Tu Nguyen, Milos Popovic, Goran Rakocevic, Walter Reade, Wonho Song, Luka Stojanovic, Erik H. Thiede, Nebojsa Tijanic, Andres Torrubia, Devin Willmott, Craig P. Butts, David R. Glowacki, Kaggle participants
The rise of machine learning (ML) has created an explosion in the potential strategies for using data to make scientific predictions.
Ranked #1 on NMR J-coupling on QM9
Formal verification techniques that compute provable guarantees on properties of machine learning models, like robustness to norm-bounded adversarial perturbations, have yielded impressive results.
In this paper, we propose an approach to differentiating through disciplined convex programs, a subclass of convex optimization problems used by domain-specific languages (DSLs) for convex optimization.
We demonstrate that by integrating this solver into end-to-end learning systems, we can learn the logical structure of challenging problems in a minimally supervised fashion.
Ranked #1 on Game of Suduko on Sudoko 9x9