Publications

2020

  1. Han, D., Tople, S., Rogers, A., Wooldridge, M., Ohrimenko, O., & Tschiatschek, S. (2020). Replication-Robust Payoff-Allocation with Applications in Machine Learning Marketplaces. https://arxiv.org/abs/2006.14583
  2. Ma, C., Tschiatschek, S., Hernández-Lobato, J. M., Turner, R., & Zhang, C. (2020). VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data. https://arxiv.org/pdf/2006.11941.pdf
  3. Ghosh, A., Tschiatschek, S., Mahdavi, H., & Singla, A. (2020). Towards Deployment of Robust Cooperative AI Agents: An Algorithmic Framework for Learning Adaptive Policies. International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS). http://ifaamas.org/Proceedings/aamas2020/pdfs/p447.pdf
  4. Beck, J., Ciosek, K., Devlin, S., Tschiatschek, S., Zhang, C., & Hofmann, K. (2020). AMRL: Aggregated Memory For Reinforcement Learning. International Conference on Learning Representations (ICLR). https://openreview.net/forum?id=Bkl7bREtDr
  5. Ma, C., Tschiatschek, S., Li, Y., Turner, R., Hernández-Lobato, J. M., & Zhang, C. (2020). HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals. Proceedings of The 2nd Symposium On Advances in Approximate Bayesian Inference, 118, 1–8. http://proceedings.mlr.press/v118/ma20a/ma20a.pdf
  6. Roth, W., Schindler, G., Zöhrer, M., Pfeifenberger, L., Peharz, R., Tschiatschek, S., Fröning, H., Pernkopf, F., & Ghahramani, Z. (2020). Resource-Efficient Neural Networks for Embedded Systems. https://arxiv.org/pdf/2001.03048.pdf

2019

  1. Ohrimenko, O., Tople, S., & Tschiatschek, S. (2019). Collaborative Machine Learning Markets with Data-Replication-Robust Payments. https://arxiv.org/pdf/1911.09052.pdf
  2. Gong, W., Tschiatschek, S., Turner, R., Nowozin, S., & Hernández-Lobato, J. M. (2019). Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model. Neural Information Processing Systems (NeurIPS). https://papers.nips.cc/paper/9621-icebreaker-element-wise-efficient-information-acquisition-with-a-bayesian-deep-latent-gaussian-model.pdf
  3. Tschiatschek, S., Ghosh, A., Haug, L., Devidze, R., & Singla, A. (2019). Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints. Neural Information Processing Systems (NeurIPS). https://papers.nips.cc/paper/8668-learner-aware-teaching-inverse-reinforcement-learning-with-preferences-and-constraints.pdf
  4. Igl, M., Ciosek, K., Li, Y., Tschiatschek, S., Zhang, C., Devlin, S., & Hofmann, K. (2019). Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck. Neural Information Processing Systems (NeurIPS). https://arxiv.org/pdf/1910.12911.pdf
  5. Janz, D., Hron, J., Mazur, P., Hofmann, K., Hernández-Lobato, J. M., & Tschiatschek, S. (2019). Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning. Neural Information Processing Systems (NeurIPS). https://arxiv.org/pdf/1810.06530.pdf
  6. Ma, C., Gong, W., Tschiatschek, S., Nowozin, S., Hernández-Lobato, J. M., & Zhang, C. (2019). Bayesian EDDI: Sequential Variable Selection with Bayesian Partial VAE. Workshop on Real-World Sequential Decision Making: Reinforcement Learning and Beyond at NeurIPS. https://realworld-sdm.github.io/paper/26.pdf

2018

  1. Haug, L., Tschiatschek, S., & Singla, A. (2018). Teaching inverse reinforcement learners via features and demonstrations. Advances in Neural Information Processing Systems (NeurIPS). https://arxiv.org/abs/1810.08926
  2. Dresdner, G., Tschiatschek, S., Gál, V., & Rätsch, G. (2018). Optimally Searching for Cancer Genes Using Submodular Models. In Workshop on Computational Biology at International Conference on Machine Learning (ICML).
  3. Ratajczak, M., Tschiatschek, S., & Pernkopf, F. (2018). Sum-Product Networks for Sequence Labeling. https://arxiv.org/pdf/1807.02324.pdf
  4. Roth, W., Peharz, R., Tschiatschek, S., & Pernkopf, F. (2018). Hybrid Generative-Discriminative Training of Gaussian Mixture Models. Pattern Recognition Letters.
  5. Tschiatschek, S., Arulkumaran, K., Stühmer, J., & Hofmann, K. (2018). Variational Inference for Data-Efficient Model Learning in POMDPs. https://arxiv.org/abs/1805.09281
  6. Tschiatschek, S., Singla, A., Gomez Rodriguez, M., Merchant, A., & Krause, A. (2018). Fake News Detection in Social Networks via Crowd Signals. Companion of the The Web Conference 2018 (WWW), 517–524. https://arxiv.org/pdf/1711.09025.pdf
  7. Tschiatschek, S., Sahin, A., & Krause, A. (2018). Differentiable Submodular Maximization. Joint Conference on Artificial Intelligence (IJCAI), 2731–2738. https://www.ijcai.org/proceedings/2018/0379.pdf
  8. Hirnschall, C., Singla, A., Tschiatschek, S., & Krause, A. (2018). Learning User Preferences to Incentivize Exploration in the Sharing Economy. Conference on Artificial Intelligence (AAAI). https://arxiv.org/pdf/1711.08331.pdf

2017

  1. Wossnig, L., Tschiatschek, S., & Zohren, S. (2017). Quantum-classical truncated Newton method for high-dimensional energy landscapes. https://arxiv.org/pdf/1710.07063.pdf
  2. Zhao, J., Djolonga, J., Tschiatschek, S., & Krause, A. (2017). Improving Optimization-Based Approximate Inference by Clamping Variables. Uncertainty in Artificial Intelligence (UAI). http://auai.org/uai2017/proceedings/papers/259.pdf
  3. Ratajczak, M., Tschiatschek, S., & Pernkopf, F. (2017). Frame and Segment Level Recurrent Neural Networks for Phone Classification. Conference of the International Speech Communication Association (Interspeech), 1318–1322. https://www.tschiatschek.net/files/ratajczak17fsrnn.pdf
  4. Bian, A. A., Buhmann, J. M., Krause, A., & Tschiatschek, S. (2017). Guarantees for Greedy Maximization of Non-submodular Functions with Applications. International Conference on Machine Learning (ICML). https://arxiv.org/pdf/1703.02100.pdf
  5. Tschiatschek, S., Singla, A., & Krause, A. (2017). Selecting Sequences of Items via Submodular Maximization. Conference on Artificial Intelligence (AAAI), 2667–2673. https://www.tschiatschek.net/files/tschiatschek17ordered.pdf

2016

  1. Djolonga, J., Jegelka, S., Tschiatschek, S., & Krause, A. (2016). Cooperative Graphical Models. Neural Information Processing Systems (NIPS). https://papers.nips.cc/paper/6122-cooperative-graphical-models.pdf
  2. Djolonga, J., Tschiatschek, S., & Krause, A. (2016). Variational Inference in Mixed Probabilistic Submodular Models. Neural Information Processing Systems (NIPS). https://papers.nips.cc/paper/6225-variational-inference-in-mixed-probabilistic-submodular-models.pdf
  3. Ratajczak, M., Tschiatschek, S., & Pernkopf, F. (2016). Virtual Adversarial Training Applied to Neural Higher-Order Factors for Phone Classification. Conference of the International Speech Communication Association (Interspeech), 2756–2760. https://www.tschiatschek.net/files/ratajczak16vat.pdf
  4. Singla, A., Tschiatschek, S., & Krause, A. (2016, June). Actively Learning Hemimetrics with Applications to Eliciting User Preferences. International Conference on Machine Learning (ICML). https://www.tschiatschek.net/files/singla16hemimetric.pdf
  5. Tschiatschek, S., Djolonga, J., & Krause, A. (2016, May). Learning Probabilistic Submodular Diversity Models Via Noise Contrastive Estimation. International Conference on Artificial Intelligence and Statistics (AISTATS). https://www.tschiatschek.net/files/tschiatschek16learning.pdf
  6. Singla, A., Tschiatschek, S., & Krause, A. (2016). Noisy Submodular Maximization via Adaptive Sampling with Applications to Crowdsourced Image Collection Summarization. Conference on Artificial Intelligence (AAAI). https://www.tschiatschek.net/files/singla16noisy.pdf

2015

  1. Ratajczak, M., Tschiatschek, S., & Pernkopf, F. (2015). Neural Higher-Order Factors in Conditional Random Fields for Phoneme Classification. Conference of the International Speech Communication Association (INTERSPEECH). https://www.tschiatschek.net/files/ratajczak15neural-higher-order.pdf
  2. Peharz, R., Tschiatschek, S., Pernkopf, F., & Domingos, P. M. (2015). On Theoretical Properties of Sum-Product Networks. International Conference on Artificial Intelligence and Statistics (AISTATS). https://www.tschiatschek.net/files/peharz15theoretical.pdf
  3. Tschiatschek, S., & Pernkopf, F. (2015). Parameter Learning of Bayesian Network Classifiers Under Computational Constraints. European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 86–101.
  4. Ratajczak, M., Tschiatschek, S., & Pernkopf, F. (2015). Structured Regularizer for Neural Higher-Order Sequence Models. European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 168–183. https://www.tschiatschek.net/files/ratajczak15StructuredRegularizer.pdf
  5. Knoll, C., Rath, M., Tschiatschek, S., & Pernkopf, F. (2015). Message Scheduling Methods for Belief Propagation. European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 295–310. https://www.tschiatschek.net/files/knoll15MessageScheduling.pdf
  6. Tschiatschek, S., & Pernkopf, F. (2015). On Reduced Precision Bayesian Network Classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 37(4). https://www.tschiatschek.net/files/tschiatschek15OnReducedPrecisionBNCs.pdf

2014

  1. Tschiatschek, S., Paul, K., & Pernkopf, F. (2014). Integer Bayesian Network Classifiers. European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 209–224.
  2. Tschiatschek, S., Iyer, R., Wei, H., & Bilmes, J. (2014). Learning Mixtures of Submodular Functions for Image Collection Summarization. Neural Information Processing Systems (NIPS). https://www.tschiatschek.net/files/tschiatschek14summarization.pdf
  3. Ratajczak, M., Tschiatschek, S., & Pernkopf, F. (2014). Sum-Product Networks for Structured Prediction: Context-Specific Deep Conditional Random Fields. https://www.tschiatschek.net/files/ratajczak14spns.pdf
  4. Pernkopf, F., Peharz, R., & Tschiatschek, S. (2014). Introduction to Probabilistic Graphical Models. In Academic Press Library in Signal Processing (Vol. 1, pp. 989–1064). Elsevier.

2013

  1. Peharz, R., Tschiatschek, S., & Pernkopf, F. (2013). The Most Generative Maximum Margin Bayesian Networks. International Conference on Machine Learning (ICML), 28, 235–243. https://www.tschiatschek.net/files/peharz13MostGenerativeMMBN.pdf
  2. Tschiatschek, S., Cancino Chacón, C. E., & Pernkopf, F. (2013). Bounds for Bayesian Network Classifiers with Reduced Precision Parameters. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 3357–3361. https://www.tschiatschek.net/files/tschiatschek13Bounds.pdf
  3. Tschiatschek, S., & Pernkopf, F. (2013). Asymptotic Optimality of Maximum Margin Bayesian Networks. International Conference on Artificial Intelligence and Statistics (AISTATS), 590–598.

2012

  1. Tschiatschek, S., Mutsam, N., & Pernkopf, F. (2012). Handling Missing Features in Maximum Margin Bayesian Network Classifiers. International Workshop on Machine Learning for Signal Processing (MLSP), 1–6.
  2. Tschiatschek, S., Reinprecht, P., Mücke, M., & Pernkopf, F. (2012). Bayesian Network Classifiers with Reduced Precision Parameters. European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 74–89.
  3. Tschiatschek, S., & Pernkopf, F. (2012). Convex Combinations of Maximum Margin Bayesian Network Classifiers. International Conference on Pattern Recognition Applications and Methods (ICPRAM).
  4. Pernkopf, F., Wohlmayr, M., & Tschiatschek, S. (2012). Maximum Margin Bayesian Network Classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 34(3), 521–531. https://www.tschiatschek.net/files/pernkopf12mmbn.pdf