Filters








54 Hits in 4.4 sec

Distilling the Knowledge from Conditional Normalizing Flows [article]

Dmitry Baranchuk, Vladimir Aliev, Artem Babenko
2021 arXiv   pre-print
We provide a positive answer to this question by proposing a simple distillation approach and demonstrating its effectiveness on state-of-the-art conditional flow-based models for image super-resolution  ...  In this work, we investigate whether one can distill flow-based models into more efficient alternatives.  ...  .), Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, pp. 2078-2087, Stockholmsmässan, Stockholm Sweden, 10-15 Jul 2018.  ... 
arXiv:2106.12699v3 fatcat:7fn3hnwtyrbqbhdvkozp2rprfm

Hyperbolic Graph Neural Networks [article]

Qi Liu, Maximilian Nickel, Douwe Kiela
2019 arXiv   pre-print
We develop a scalable algorithm for modeling the structural properties of graphs, comparing Euclidean and hyperbolic geometry.  ...  Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise.  ...  In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 2328–2337, 2018. [26] Thomas N.  ... 
arXiv:1910.12892v1 fatcat:zpc5bwjlyrbbxlwvnflxr4jv4y

KNAS: Green Neural Architecture Search [article]

Jingjing Xu, Liang Zhao, Junyang Lin, Rundong Gao, Xu Sun, Hongxia Yang
2021 arXiv   pre-print
Experiments show that KNAS achieves competitive results with orders of magnitude faster than "train-then-test" paradigms on image classification tasks.  ...  Furthermore, the extremely low search cost enables its wide applications. The searched network also outperforms strong baseline RoBERTA-large on two text classification tasks. Codes are available at .  ...  In Proceedings of the 36th International Conference on Machine Learning, pp. 4095– International Conference on Machine Learning, ICML 4104.  ... 
arXiv:2111.13293v1 fatcat:fz4p37bk2jgxnn2qfc6ffvvfwu

Variational Neural Machine Translation with Normalizing Flows [article]

Hendra Setiawan, Matthias Sperber, Udhay Nallasamy, Matthias Paulik
2020 arXiv   pre-print
Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables  ...  Previous works impose strong assumptions on the distribution of the latent code and limit the choice of the NMT architecture.  ...  In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 159-168.  ... 
arXiv:2005.13978v1 fatcat:7ysqtt4kgzgm3l4kddct7byihy

Learning Compressed Transforms with Low Displacement Rank [article]

Anna T. Thomas and Albert Gu and Tri Dao and Atri Rudra and Christopher Ré
2019 arXiv   pre-print
We prove bounds on the VC dimension of multi-layer neural networks with structured weight matrices and show empirically that our compact parameterization can reduce the sample complexity of learning.  ...  We introduce a class of LDR matrices with more general displacement operators, and explicitly learn over both the operators and the low-rank component.  ...  , of DARPA, NIH, ONR, or the U.S.  ... 
arXiv:1810.02309v3 fatcat:hf2tf74hn5hojfmhzo54gt6fhm

PARL: Enhancing Diversity of Ensemble Networks to Resist Adversarial Attacks via Pairwise Adversarially Robust Loss Function [article]

Manaar Alam, Shubhajit Datta, Debdeep Mukhopadhyay, Arijit Mondal, Partha Pratim Chakrabarti
2021 arXiv   pre-print
The security of Deep Learning classifiers is a critical field of study because of the existence of adversarial attacks.  ...  Such attacks usually rely on the principle of transferability, where an adversarial example crafted on a surrogate classifier tends to mislead the target classifier trained on the same dataset even if  ...  , Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, volume 80 of Proceedings of Machine Learning Research, pages 274–283.  ... 
arXiv:2112.04948v1 fatcat:i7ab4hvgprcgvdpnowrlwmaiwa

Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics [article]

Prajjwal Bhargava, Aleksandr Drozd, Anna Rogers
2021 arXiv   pre-print
Much of recent progress in NLU was shown to be due to models' learning dataset-specific heuristics.  ...  We conduct a case study of generalization in NLI (from MNLI to the adversarially constructed HANS dataset) in a range of BERT-based architectures (adapters, Siamese Transformers, HEX debiasing), as well  ...  In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, volume 80 of Proceedings of Ma- chine Learning Research, pages  ... 
arXiv:2110.01518v1 fatcat:orftxwh7uvcwdkpamabwqzxgti

A Novel Sequential Coreset Method for Gradient Descent Algorithms [article]

Jiawei Huang, Ruomin Huang, Wenjie Liu, Nikolaos M. Freris, Hu Ding
2021 arXiv   pre-print
A wide range of optimization problems arising in machine learning can be solved by gradient descent algorithms, and a central question in this area is how to efficiently compress a large-scale dataset  ...  In this paper, based on the "locality" property of gradient descent algorithms, we propose a new framework, termed "sequential coreset", which effectively avoids these obstacles.  ...  Dy and Andreas Krause, ed- itors, Proceedings of the 35th International Conference on Machine Learn- ing, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, volume 80 of  ... 
arXiv:2112.02504v1 fatcat:ca6ik4vfgfgqrmoqottujcbhwa

Deep Learning for Text Style Transfer: A Survey [article]

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 arXiv   pre-print
We also provide discussions on a variety of important topics regarding the future development of this task. Our curated paper list is at https://github.com/zhijing-jin/Text_Style_Transfer_Survey  ...  In this paper, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017.  ...  Conference on Machine Learning, ICML 2018, Zhang, Jingyi, Masao Utiyama, Eiichiro Stockholmsmässan, Stockholm, Sweden, July Sumita, Graham Neubig, and Satoshi 10-15, 2018,  ... 
arXiv:2011.00416v5 fatcat:wfw3jfh2mjfupbzrmnztsqy4ny

Automated Discovery of Adaptive Attacks on Adversarial Defenses [article]

Chengyuan Yao, Pavol Bielik, Petar Tsankov, Martin Vechev
2021 arXiv   pre-print
We evaluated our approach on 24 adversarial defenses and show that it outperforms AutoAttack, the current state-of-the-art tool for reliable evaluation of adversarial defenses: our tool discovered significantly  ...  Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble  ...  (eds.), Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, volume 80 of Proceedings of Machine Learning Research, pp  ... 
arXiv:2102.11860v3 fatcat:fewctvqk6zg4bagc4lvstpqrgq

FNNC: Achieving Fairness through Neural Networks [article]

Padala Manisha, Sujit Gujar
2020 arXiv   pre-print
The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better.  ...  The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero.  ...  In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 3381-3390, 2018.  ... 
arXiv:1811.00247v3 fatcat:rjtpzeo3nng4jgjpa7avklfod4

Query complexity of adversarial attacks [article]

Grzegorz Głuch, Rüdiger Urbanke
2021 arXiv   pre-print
We give a lower bound on that number of queries in terms of entropy of decision boundaries of the classifier.  ...  Using this result we analyze two classical learning algorithms on two synthetic tasks for which we prove meaningful security guarantees.  ...  In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pp. 274-283, 2018.  ... 
arXiv:2010.01039v2 fatcat:th5mrgldfnahfl2n3bp6uokybm

On the Effectiveness of Iterative Learning Control [article]

Anirudh Vemula, Wen Sun, Maxim Likhachev, J. Andrew Bagnell
2021 arXiv   pre-print
Iterative learning control (ILC) is a powerful technique for high performance tracking in the presence of modeling errors for optimal control applications.  ...  Our work presents such a theoretical study of the performance of both ILC and MM on Linear Quadratic Regulator (LQR) problems with unknown transition dynamics.  ...  Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, volume 80 of Proceedings of  ... 
arXiv:2111.09434v3 fatcat:lwnqcrx4wneiddqrgwq2dpke4q

Deep Learning for Text Style Transfer: A Survey

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 Computational Linguistics  
We also provide discussions on a variety of important topics regarding the future development of this task.  ...  In this paper, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017.  ...  Conference on Machine Learning, ICML 2018, Zhang, Jingyi, Masao Utiyama, Eiichiro Stockholmsmässan, Stockholm, Sweden, July Sumita, Graham Neubig, and Satoshi 10-15, 2018  ... 
doi:10.1162/coli_a_00426 fatcat:v7vmb62ckfcu5k5mpu2pydnrxy

Regex Queries over Incomplete Knowledge Bases [article]

Vaibhav Adlakha, Parth Shah, Srikanta Bedathur, Mausam
2021 arXiv   pre-print
We demonstrate performance of RotatE-Box on two new regex-query datasets introduced in this paper, including one where the queries are harvested based on actual user query logs.  ...  We propose the novel task of answering regular expression queries (containing disjunction (∨) and Kleene plus (+) operators) over incomplete KBs.  ...  In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 2869-2878. Ni Lao, Tom Mitchell, and William W.  ... 
arXiv:2005.00480v2 fatcat:c3f6m437pvarzffdggvovzvmka
« Previous Showing results 1 — 15 out of 54 results