Fetching the paper…
Reading the bibliography…
We present strong mixed-integer programming (MIP) formulations for high-dimensional piecewise linear functions that correspond to trained neural networks.
https://arxiv.org/abs/1902.08722
Salman, H., Yang, G., Zhang, H., Hsieh, C.J., Zhang, P.: A convex relaxation barrier to tight robustness verification of neural networks (2019) · 1902
Earlier work this paper cites.
https://arxiv.org/abs/1903.06758
Liu, C., Arnon, T., Lazarus, C., Barrett, C., Kochenderfer, M.J.: Algorithms for verifying deep neural networks (2019) · 1903
Earlier work this paper cites.
https://arxiv.org/abs/1905.11428
Kumar, A., Serra, T., Ramalingam, S.: Equivalent and approximate transformations of deep neural networks (2019) · 1905
Earlier work this paper cites.
https://arxiv.org/abs/1909.12397
Ryu, M., Chow, Y., Anderson, R., Tjandraatmadja, C., Boutilier, C.: CAQL: Continuous action Q-learning (2019) · 1909
Earlier work this paper cites.
Mathematical Programming Study 22
Jeroslow, R., Lowe, J.: Modelling with integer variables · 1984
Earlier work this paper cites.
SIAM Journal on Algorithmic Discrete Methods 6
Balas, E.: Disjunctive programming and a hierarchy of relaxations for discrete optimization problems · 1985
Earlier work this paper cites.
In: Stochastic Programming 84 Part I, pp. 153–182. Springer (1986)
Haneveld, W.K.K.: Robustness against dependence in pert: An application of duality and distributions with known marginals · 1986
Earlier work this paper cites.
Operations Research 34
Weiss, G.: Stochastic bounds on distributions of optimal value functions with applications to pert, network flows and reliability · 1986
Earlier work this paper cites.
Annals of Operations Research 12
Jeroslow, R.G.: Alternative formulations of mixed integer programs · 1988
Earlier work this paper cites.
Athena Scientific (1997)
Bertsimas, D., Tsitsiklis, J.: Introduction to Linear Optimization · 1997
Earlier work this paper cites.
Discrete Applied Mathematics 89
Balas, E.: Disjunctive programming: Properties of the convex hull of feasible points · 1998
Earlier work this paper cites.
In: Proceedings of the IEEE, vol. 86, pp. 2278–2324 (1998)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition · 1998
Earlier work this paper cites.
Journal of the European Mathematical Society 2
Huber, B., Rambau, J., Santos, F.: The Cayley Trick, lifting subdivisions and the Bohne-Dress theorem of zonotopal tiltings · 2000
Earlier work this paper cites.
Springer (2000)
Korte, B., Vygen, J.: Combinatorial Optimization: Theory and Algorithms · 2000
Earlier work this paper cites.
Springer Science & Business Media (2002)
Tawarmalani, M., Sahinidis, N.: Convexification and Global Optimization in Continuous and Mixed-Integer Nonlinear Programming: Theory, Algorithms, Software and Applications, vol. 65 · 2002
Earlier work this paper cites.
Springer (2006)
Bishop, C.M.: Pattern Recognition and Machine Learning · 2006
Earlier work this paper cites.
Ph.D. thesis, École Polytechnique Fédérale de Lausanne (2007)
Weibel, C.: Minkowski sums of polytopes: Combinatorics and computation · 2007
Earlier work this paper cites.
Management Science 55
Natarajan, K., Song, M., Teo, C.P.: Persistency model and its applications in choice modeling · 2009
Earlier work this paper cites.
In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2559–2566 (2010)
Boureau, Y.L., Bach, F., LeCun, Y., Ponce, J.: Learning mid-level features for recognition · 2010
Earlier work this paper cites.
In: International Conference on the Principles and Practice of Constraint Programming, pp. 115–129. Springer, Berlin, Heidelberg (2011)
Bartolini, A., Lombardi, M., Milano, M., Benini, L.: Neuron constraints to model complex real-world problems · 2011
Earlier work this paper cites.
In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp. 315–323 (2011)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks · 2011
Earlier work this paper cites.
Mathematical Programming 128
Vielma, J.P., Nemhauser, G.: Modeling disjunctive constraints with a logarithmic number of binary variables and constraints · 2011
Earlier work this paper cites.
In: Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, pp. 427–433 (2012)
Bartolini, A., Lombardi, M., Milano, M., Benini, L.: Optimization and controlled systems: A case study on thermal aware workload dispatching · 2012
Earlier work this paper cites.
Computational Optimization and Applications 52
Hijazi, H., Bonami, P., Cornuéjols, G., Ouorou, A.: Mixed-integer nonlinear programs featuring ”on/off” constraints · 2012
Earlier work this paper cites.
In: Proceedings of the 30th International Conference on Machine Learning, vol. 28, pp. 1319–1327 (2013)
Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks · 2013
Earlier work this paper cites.
In: ICML Workshop on Deep Learning for Audio, Speech and Language (2013)
Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models · 2013
Earlier work this paper cites.
http://www.optimization-online.org/DB_FILE/2014/04/4309.pdf
Hijazi, H., Bonami, P., Ouorou, A.: A note on linear on/off constraints (2014) · 2014
Earlier work this paper cites.
https://arxiv.org/abs/1412.6980
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization (2014) · 2014
Earlier work this paper cites.
In: International Conference on Learning Representations (2014)
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R.: Intriguing properties of neural networks · 2014
Cited alongside, same era.
Nature Biotechnology 33
Alipanahi, B., Delong, A., Weirauch, M.T., Frey, B.J.: Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning · 2015
Cited alongside, same era.
Mathematical Programming 151
Bonami, P., Lodi, A., Tramontani, A., Wiese, S.: On mathematical programming with indicator constraints · 2015
Cited alongside, same era.
https://arxiv.org/abs/1512.07679
Dulac-Arnold, G., Evans, R., van Hasselt, H., Sunehag, P., Lillicrap, T., Hunt, J., Mann, T., Weber, T., Degris, T., Coppin, B.: Deep reinforcement learning in large discrete action spaces (2015) · 2015
Cited alongside, same era.
https://arxiv.org/abs/1508.06576
Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style (2015) · 2015
Cited alongside, same era.
Distill (2017)
Olah, C., Mordvintsev, A., Schubert, L.: Feature visualization · 2017
Later among the works it cites.
In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, pp. 750–756 (2017)
Say, B., Wu, G., Zhou, Y.Q., Sanner, S.: Nonlinear hybrid planning with deep net learned transition models and mixed-integer linear programming · 2017
Later among the works it cites.
In: Advances in Neural Information Processing Systems, pp. 6276–6286 (2017)
Wu, G., Say, B., Sanner, S.: Scalable planning with Tensorflow for hybrid nonlinear domains · 2017
Later among the works it cites.
Mathematical Programming (2018)
Atamtürk, A., Gómez, A.: Strong formulations for quadratic optimization with M-matrices and indicator variables · 2018
Closest in time.
arXiv preprint arXiv:1810.03218 (2018)
Bienstock, D., Muñoz, G., Pokutta, S.: Principled deep neural network training through linear programming · 2018
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Nature 521
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning · 2015
Cited alongside, same era.
https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html
Mordvintsev, A., Olah, C., Tyka, M.: Inceptionism: Going deeper into neural networks (2015) · 2015
Cited alongside, same era.
Computers and Chemical Engineering 76
Trespalacios, F., Grossmann, I.E.: Improved big-M reformulation for generalized disjunctive programs · 2015
Cited alongside, same era.
SIAM Review 57
Vielma, J.P.: Mixed integer linear programming formulation techniques · 2015
Cited alongside, same era.
https://arxiv.org/abs/1505.00853
Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolution network (2015) · 2015
Cited alongside, same era.
arXiv preprint arXiv:1611.01491 (2016)
Arora, R., Basu, A., Mianjy, P., Mukherjee, A.: Understanding deep neural networks with rectified linear units · 2016
Cited alongside, same era.
In: Advances in Neural Information Processing Systems, pp. 2613–2621 (2016)
Bastani, O., Ioannou, Y., Lampropoulos, L., Vytiniotis, D., Nori, A.V., Criminisi, A.: Measuring neural net robustness with constraints · 2016
Cited alongside, same era.
In: Advances in Neural Information Processing Systems (2018)
Bunel, R., Turkaslan, I., Torr, P.H., Kohli, P., Kumar, M.P.: A unified view of piecewise linear neural network verification · 2018
Closest in time.
Available at SSRN 3159473 (2018)
Chen, L., Ma, W., Natarajan, K., Simchi-Levi, D., Yan, Z.: Distributionally robust linear and discrete optimization with marginals · 2018
Closest in time.
In: NASA Formal Methods Symposium (2018)
Dutta, S., Jha, S., Sanakaranarayanan, S., Tiwari, A.: Output range analysis for deep feedforward neural networks · 2018
Closest in time.
https://arxiv.org/abs/1805.10265
Dvijotham, K., Gowal, S., Stanforth, R., Arandjelovic, R., O’Donoghue, B., Uesato, J., Kohli, P.: Training verified learners with learned verifiers (2018) · 2018
Closest in time.
In: Thirty-Fourth Conference Annual Conference on Uncertainty in Artificial Intelligence (2018)
Dvijotham, K., Stanforth, R., Gowal, S., Mann, T., Kohli, P.: A dual approach to scalable verification of deep networks · 2018
Closest in time.
Constraints (2018)
Fischetti, M., Jo, J.: Deep neural networks and mixed integer linear optimization · 2018
Closest in time.
Ph.D. thesis, Massachusetts Institute of Technology (2018)
Huchette, J.: Advanced mixed-integer programming formulations: Methodology, computation, and application · 2018
Closest in time.
In: Proceedings IJCAI, pp. 5472–5478 (2018)
Lombardi, M., Milano, M.: Boosting combinatorial problem modeling with machine learning · 2018
Closest in time.
In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS’18, pp. 10,900–10,910. Curran Associates Inc. (2018)
Raghunathan, A., Steinhardt, J., Liang, P.: Semidefinite relaxations for certifying robustness to adversarial examples · 2018
Closest in time.
Journal of Optimization Theory and Applications (2018)
Schweidtmann, A.M., Mitsos, A.: Global deterministic optimization with artificial neural networks embedded · 2018
Closest in time.
https://arxiv.org/abs/1810.03370
Serra, T., Ramalingam, S.: Empirical bounds on linear regions of deep rectifier networks (2018) · 2018
Closest in time.
In: Thirty-fifth International Conference on Machine Learning (2018)
Serra, T., Tjandraatmadja, C., Ramalingam, S.: Bounding and counting linear regions of deep neural networks · 2018
Closest in time.
Management Science 64
Vielma, J.P.: Embedding formulations and complexity for unions of polyhedra · 2018
Closest in time.
Mathematical Programming (2018)
Vielma, J.P.: Small and strong formulations for unions of convex sets from the Cayley embedding · 2018
Closest in time.
In: International Conference on Machine Learning (2018)
Wong, E., Kolter, J.Z.: Provable defenses against adversarial examples via the convex outer adversarial polytope · 2018
Closest in time.
In: 32nd Conference on Neural Information Processing Systems (2018)
Wong, E., Schmidt, F., Metzen, J.H., Kolter, J.Z.: Scaling provable adversarial defenses · 2018
Closest in time.
Anderson, R., Huchette, J., Tjandraatmadja, C., Vielma, J.P.: Strong mixed-integer programming formulations for trained neural networks · 2019
Closest in time.
In: K. Chaudhuri, R. Salakhutdinov (eds.) Proceedings of the 36th International Conference on Machine Learning, Proceedings of Machine Learning Research , vol. 97, pp. 1802–1811. PMLR, Long Beach, California, USA (2019)
Engstrom, L., Tran, B., Tsipras, D., Schmidt, L., Madry, A.: Exploring the landscape of spatial robustness · 2019
Closest in time.
Computers & Chemical Engineering 131
Grimstad, B., Andersson, H.: ReLU networks as surrogate models in mixed-integer linear programs · 2019
Closest in time.
In: International Conference on Learning Representations (2019)
Khalil, E.B., Gupta, A., Dilkina, B.: Combinatorial attacks on binarized neural networks · 2019
Closest in time.
In: International Conference on Learning Representations (2019)
Tjeng, V., Xiao, K., Tedrake, R.: Verifying neural networks with mixed integer programming · 2019
Closest in time.
In: International Conference on Learning Representations (2019)
Xiao, K.Y., Tjeng, V., Shafiullah, N.M., Madry, A.: Training for faster adversarial robustness verification via inducing ReLU stability · 2019
Closest in time.