no code implementations • 24 Jan 2024 • Timothée Schmude, Laura Koesten, Torsten Möller, Sebastian Tschiatschek
Explanations of AI systems rarely address the information needs of people affected by algorithmic decision-making (ADM).
no code implementations • 27 Dec 2023 • Timo Klein, Susanna Weinberger, Adish Singla, Sebastian Tschiatschek
We consider the problem of third-person imitation learning with the additional challenge that the learner must select the perspective from which they observe the expert.
no code implementations • 25 Oct 2023 • Timur Sudak, Sebastian Tschiatschek
We consider the problem of learning Variational Autoencoders (VAEs), i. e., a type of deep generative model, from data with missing values.
no code implementations • 15 Oct 2023 • Manh Hung Nguyen, Sebastian Tschiatschek, Adish Singla
We instantiate several methods based on LLM-SS framework and evaluate them using an existing benchmark, StudentSyn, for student attempt synthesis in a visual programming domain.
no code implementations • 26 May 2023 • Timothée Schmude, Laura Koesten, Torsten Möller, Sebastian Tschiatschek
We argue that explanations for "algorithmic decision-making" (ADM) systems can profit by adopting practices that are already used in the learning sciences.
1 code implementation • 25 May 2023 • David Lindner, Xin Chen, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause
We evaluate CoCoRL in gridworld environments and a driving simulation with multiple constraints.
1 code implementation • 28 Mar 2023 • Ahana Ghosh, Sebastian Tschiatschek, Sam Devlin, Adish Singla
We introduce a scaffolding framework based on pop quizzes presented as multi-choice programming tasks.
1 code implementation • 10 Jun 2022 • David Lindner, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause
We provide an instance-dependent lower bound for constrained linear best-arm identification and show that ACOL's sample complexity matches the lower bound in the worst-case.
no code implementations • 4 May 2022 • Sebastian Tschiatschek, Maria Knobelsdorf, Adish Singla
We consider the equity and fairness of curricula derived from Knowledge Tracing models.
no code implementations • 18 Oct 2021 • Dongge Han, Sebastian Tschiatschek
Abstraction plays an important role in the generalisation of knowledge and skills and is key to sample efficient learning.
no code implementations • 12 Apr 2021 • Angus Lamb, Evgeny Saveliev, Yingzhen Li, Sebastian Tschiatschek, Camilla Longden, Simon Woodhead, José Miguel Hernández-Lobato, Richard E. Turner, Pashmina Cameron, Cheng Zhang
While deep learning has obtained state-of-the-art results in many applications, the adaptation of neural network architectures to incorporate new output features remains a challenge, as neural networks are commonly trained to produce a fixed output dimension.
1 code implementation • NeurIPS 2021 • David Lindner, Matteo Turchetta, Sebastian Tschiatschek, Kamil Ciosek, Andreas Krause
For many reinforcement learning (RL) applications, specifying a reward is difficult.
no code implementations • NeurIPS Workshop LMCA 2020 • Haiyan Yin, Yingzhen Li, Sinno Jialin Pan, Cheng Zhang, Sebastian Tschiatschek
Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem.
no code implementations • 25 Jun 2020 • Dongge Han, Michael Wooldridge, Alex Rogers, Olga Ohrimenko, Sebastian Tschiatschek
In this paper, we systematically study the replication manipulation in submodular games and investigate replication robustness, a metric that quantitatively measures the robustness of solution concepts against replication.
2 code implementations • NeurIPS 2020 • Chao Ma, Sebastian Tschiatschek, José Miguel Hernández-Lobato, Richard Turner, Cheng Zhang
Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets.
no code implementations • ICLR 2020 • Jacob Beck, Kamil Ciosek, Sam Devlin, Sebastian Tschiatschek, Cheng Zhang, Katja Hofmann
In many partially observable scenarios, Reinforcement Learning (RL) agents must rely on long-term memory in order to learn an optimal policy.
no code implementations • 12 Mar 2020 • Zichao Wang, Sebastian Tschiatschek, Simon Woodhead, Jose Miguel Hernandez-Lobato, Simon Peyton Jones, Richard G. Baraniuk, Cheng Zhang
Online education platforms enable teachers to share a large number of educational resources such as questions to form exercises and quizzes for students.
no code implementations • 7 Jan 2020 • Wolfgang Roth, Günther Schindler, Bernhard Klein, Robert Peharz, Sebastian Tschiatschek, Holger Fröning, Franz Pernkopf, Zoubin Ghahramani
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches.
1 code implementation • NeurIPS 2019 • Wenbo Gong, Sebastian Tschiatschek, Sebastian Nowozin, Richard E. Turner, José Miguel Hernández-Lobato, Cheng Zhang
In this paper, we address the ice-start problem, i. e., the challenge of deploying machine learning models when only a little or no training data is initially available, and acquiring each feature element of data is associated with costs.
no code implementations • 8 Nov 2019 • Olga Ohrimenko, Shruti Tople, Sebastian Tschiatschek
We study the problem of collaborative machine learning markets where multiple parties can achieve improved performance on their machine learning tasks by combining their training data.
1 code implementation • NeurIPS 2019 • Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin, Katja Hofmann
We discuss those differences and propose modifications to existing regularization techniques in order to better adapt them to RL.
no code implementations • pproximateinference AABI Symposium 2019 • Chao Ma, Sebastian Tschiatschek, Yingzhen Li, Richard Turner, Jose Miguel Hernandez-Lobato, Cheng Zhang
In this paper, we focused on improving VAEs for real-valued data that has heterogeneous marginal distributions.
no code implementations • 5 Oct 2019 • Ahana Ghosh, Sebastian Tschiatschek, Hamed Mahdavi, Adish Singla
In the test phase, the AI agent has to interact with a user of unknown type.
1 code implementation • 13 Aug 2019 • Wenbo Gong, Sebastian Tschiatschek, Richard Turner, Sebastian Nowozin, José Miguel Hernández-Lobato, Cheng Zhang
In this paper we introduce the ice-start problem, i. e., the challenge of deploying machine learning models when only little or no training data is initially available, and acquiring each feature element of data is associated with costs.
no code implementations • NeurIPS 2019 • Sebastian Tschiatschek, Ahana Ghosh, Luis Haug, Rati Devidze, Adish Singla
We study two teaching approaches: learner-agnostic teaching, where the teacher provides demonstrations from an optimal policy ignoring the learner's preferences, and learner-aware teaching, where the teacher accounts for the learner's preferences.
no code implementations • 5 Dec 2018 • Franz Pernkopf, Wolfgang Roth, Matthias Zoehrer, Lukas Pfeifenberger, Guenther Schindler, Holger Froening, Sebastian Tschiatschek, Robert Peharz, Matthew Mattina, Zoubin Ghahramani
In that way, we provide an extensive overview of the current state-of-the-art of robust and efficient machine learning for real-world systems.
no code implementations • NeurIPS 2018 • Luis Haug, Sebastian Tschiatschek, Adish Singla
In this paper, we study the problem of learning from demonstrations in the setting where this is not the case, i. e., where there is a mismatch between the worldviews of the learner and the expert.
2 code implementations • NeurIPS 2019 • David Janz, Jiri Hron, Przemysław Mazur, Katja Hofmann, José Miguel Hernández-Lobato, Sebastian Tschiatschek
Posterior sampling for reinforcement learning (PSRL) is an effective method for balancing exploration and exploitation in reinforcement learning.
1 code implementation • ICLR 2019 • Chao Ma, Sebastian Tschiatschek, Konstantina Palla, José Miguel Hernández-Lobato, Sebastian Nowozin, Cheng Zhang
Many real-life decision-making situations allow further relevant information to be acquired at a specific cost, for example, in assessing the health status of a patient we may decide to take additional measurements such as diagnostic tests or imaging scans before making a final assessment.
no code implementations • 6 Jul 2018 • Martin Ratajczak, Sebastian Tschiatschek, Franz Pernkopf
We consider higher-order linear-chain conditional random fields (HO-LC-CRFs) for sequence modelling, and use sum-product networks (SPNs) for representing higher-order input- and output-dependent factors.
Optical Character Recognition Optical Character Recognition (OCR)
no code implementations • 23 May 2018 • Sebastian Tschiatschek, Kai Arulkumaran, Jan Stühmer, Katja Hofmann
In this paper we propose DELIP, an approach to model learning for POMDPs that utilizes amortized structured variational inference.
no code implementations • 5 Mar 2018 • Sebastian Tschiatschek, Aytunc Sahin, Andreas Krause
We consider learning of submodular functions from data.
no code implementations • 24 Nov 2017 • Sebastian Tschiatschek, Adish Singla, Manuel Gomez Rodriguez, Arpit Merchant, Andreas Krause
The main objective of our work is to minimize the spread of misinformation by stopping the propagation of fake news in the network.
Social and Information Networks
no code implementations • 17 Nov 2017 • Christoph Hirnschall, Adish Singla, Sebastian Tschiatschek, Andreas Krause
We provide formal guarantees on the performance of our algorithm and test the viability of our approach in a user study with data of apartments on Airbnb.
1 code implementation • ICML 2017 • Andrew An Bian, Joachim M. Buhmann, Andreas Krause, Sebastian Tschiatschek
Our guarantees are characterized by a combination of the (generalized) curvature $\alpha$ and the submodularity ratio $\gamma$.
no code implementations • 9 Feb 2017 • Christoph Hirnschall, Adish Singla, Sebastian Tschiatschek, Andreas Krause
We study an online multi-task learning setting, in which instances of related tasks arrive sequentially, and are handled by task-specific online learners.
no code implementations • NeurIPS 2016 • Josip Djolonga, Stefanie Jegelka, Sebastian Tschiatschek, Andreas Krause
We study a rich family of distributions that capture variable interactions significantly more expressive than those representable with low-treewidth or pairwise graphical models, or log-supermodular models.
no code implementations • NeurIPS 2016 • Josip Djolonga, Sebastian Tschiatschek, Andreas Krause
We consider the problem of variational inference in probabilistic models with both log-submodular and log-supermodular higher-order potentials.
no code implementations • 23 May 2016 • Adish Singla, Sebastian Tschiatschek, Andreas Krause
We propose an active learning algorithm that substantially reduces this sample complexity by exploiting the structural constraints on the version space of hemimetrics.
no code implementations • 23 Nov 2015 • Adish Singla, Sebastian Tschiatschek, Andreas Krause
When the underlying submodular function is unknown, users' feedback can provide noisy evaluations of the function that we seek to maximize.
no code implementations • NeurIPS 2014 • Sebastian Tschiatschek, Rishabh K. Iyer, Haochen Wei, Jeff A. Bilmes
This paper provides, to our knowledge, the first systematic approach for quantifying the problem of image collection summarization, along with a new dataset of image collections and human summaries.