Max B. Paulus PhD Student max.paulus@inf.ethz.ch CAB E 65.2 +41 44 632 71 48 Publications 2022 Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs Đ. Miladinovi\’c, K. Shridhar, K. Jain, M. B. Paulus, J. M. Buhmann, C. AllenIn Proc. Neural Information Processing Systems (NeurIPS), 2022[bibtex] [abstract] [pdf] Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning M. B. Paulus, G. Zarpellon, A. Krause, L. Charlin, C. J. MaddisonIn Proc. International Conference on Machine Learning (ICML), 2022[bibtex] [abstract] [pdf] A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning I. A. M. Huijben, W. Kool, M. B. Paulus, R. J. Van SlounIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022[bibtex] [abstract] [pdf] Augment with Care: Contrastive Learning for Combinatorial Problems H. Duan, P. Vaezipoor, M. B. Paulus, Y. Ruan, C. MaddisonIn International Conference on Machine Learning, 2022[bibtex] [abstract] [pdf] [code] 2021 Instance-wise algorithm configuration with graph neural networks R. Valentin, C. Ferrari, J. Scheurer, A. Amrollahi, C. Wendler, M. B. PaulusNeurIPS Machine Learning for Combinatorial Optimization Competition, 2021Student Winner[bibtex] [abstract] [pdf] [code] Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator M. B. Paulus, C. J. Maddison, A. KrauseIn Proc. International Conference on Learning Representations (ICLR), 2021Oral presentation[bibtex] [abstract] [pdf] 2020 Gradient Estimation with Stochastic Softmax Tricks M. B. Paulus, D. Choi, D. Tarlow, A. Krause, C. J. MaddisonIn Proc. Neural Information Processing Systems (NeurIPS), 2020Oral presentation[bibtex] [abstract] [pdf] [code]
