English
Related papers

Related papers: BaNEL: Exploration Posteriors for Generative Model…

200 papers

Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics. However, a major challenge in training agents from learned reward models is that the agent can learn to exploit…

Machine Learning · Computer Science 2019-11-04 Danfei Xu , Misha Denil

It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are…

Computer Vision and Pattern Recognition · Computer Science 2020-12-07 Patrick Esser , Robin Rombach , Björn Ommer

We introduce a new approach to functional causal modeling from observational data, called Causal Generative Neural Networks (CGNN). CGNN leverages the power of neural networks to learn a generative model of the joint distribution of the…

Generative adversarial networks (GANs) are designed with the help of min-max optimization problems that are solved with stochastic gradient-type algorithms which are known to be non-robust. In this work we revisit a non-adversarial method…

Machine Learning · Computer Science 2018-11-26 Kalliopi Basioti , George V. Moustakides , Emmanouil Z. Psarakis

An effective reward model plays a pivotal role in reinforcement learning for post-training enhancement of visual generative models. However, current approaches of reward modeling suffer from implementation complexity due to their reliance…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Runtao Liu , Jiahao Zhan , Yingqing He , Chen Wei , Alan Yuille , Qifeng Chen

Continual Learning is an unresolved challenge, whose relevance increases when considering modern applications. Unlike the human brain, trained deep neural networks suffer from a phenomenon called catastrophic forgetting, wherein they…

Machine Learning · Computer Science 2025-02-18 Shahar Shaul-Ariel , Daphna Weinshall

Generative models are widely used for unsupervised learning with various applications, including data compression and signal restoration. Training methods for such systems focus on the generality of the network given limited amount of…

Computer Vision and Pattern Recognition · Computer Science 2017-08-31 Asim Munawar , Phongtharin Vinayavekhin , Giovanni De Magistris

Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy…

Machine Learning · Computer Science 2020-10-26 Amina Mollaysa , Brooks Paige , Alexandros Kalousis

Sufficient supervised information is crucial for any machine learning models to boost performance. However, labeling data is expensive and sometimes difficult to obtain. Active learning is an approach to acquire annotations for data from a…

Machine Learning · Computer Science 2019-06-18 Quan Kong , Bin Tong , Martin Klinkigt , Yuki Watanabe , Naoto Akira , Tomokazu Murakami

Neural Network-based active learning (NAL) is a cost-effective data selection technique that utilizes neural networks to select and train on a small subset of samples. While existing work successfully develops various effective or…

Machine Learning · Computer Science 2024-06-07 Dake Bu , Wei Huang , Taiji Suzuki , Ji Cheng , Qingfu Zhang , Zhiqiang Xu , Hau-San Wong

Prediction failures of machine learning models often arise from deficiencies in training data, such as incorrect labels, outliers, and selection biases. However, such data points that are responsible for a given failure mode are generally…

Machine Learning · Computer Science 2022-11-11 Ryutaro Tanno , Melanie F. Pradier , Aditya Nori , Yingzhen Li

Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine…

Machine Learning · Computer Science 2020-07-01 Kristy Choi , Aditya Grover , Trisha Singh , Rui Shu , Stefano Ermon

Devising procedures for downstream task-oriented generative model selections is an unresolved problem of practical importance. Existing studies focused on the utility of a single family of generative models. They provided limited insights…

Machine Learning · Computer Science 2024-01-03 Yinan Cheng , Chi-Hua Wang , Vamsi K. Potluru , Tucker Balch , Guang Cheng

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

We showed how to use trained neural networks to perform Bayesian reasoning in order to solve tasks outside their initial scope. Deep generative models provide prior knowledge, and classification/regression networks impose constraints. The…

Machine Learning · Computer Science 2021-06-02 Jakob Knollmüller , Torsten Enßlin

Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance. If we see these implicit…

Machine Learning · Statistics 2019-11-05 Arash Mehrjou , Wittawat Jitkrittum , Krikamol Muandet , Bernhard Schölkopf

Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance. If we see these implicit…

Machine Learning · Computer Science 2019-11-07 Arash Mehrjou , Wittawat Jitkrittum , Krikamol Muandet , Bernhard Schölkopf

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as…

Machine Learning · Computer Science 2026-02-18 Raphaël Baur , Yannick Metz , Maria Gkoulta , Mennatallah El-Assady , Giorgia Ramponi , Thomas Kleine Buening

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned reward models makes it vulnerable to mis-specification and reward hacking. Preference-based…

Machine Learning · Computer Science 2026-04-23 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC)…

Machine Learning · Computer Science 2021-04-16 Minghuan Liu , Tairan He , Minkai Xu , Weinan Zhang