English
Related papers

Related papers: Gibbs-Duhem-Informed Neural Networks for Binary Ac…

200 papers

We provide an information-theoretic analysis of the generalization ability of Gibbs-based transfer learning algorithms by focusing on two popular transfer learning approaches, $\alpha$-weighted-ERM and two-stage-ERM. Our key result is an…

Machine Learning · Computer Science 2021-11-03 Yuheng Bu , Gholamali Aminian , Laura Toni , Miguel Rodrigues , Gregory Wornell

Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation. Such an approach requires either some heuristics to sample a batch of design points at one…

Machine Learning · Computer Science 2020-01-28 Evgenii Tsymbalov , Sergei Makarychev , Alexander Shapeev , Maxim Panov

We propose a double/debiased machine learning framework to estimate average derivative effects in nonparametric panel models with two-way fixed effects. It extends instrumental variable methods to panel settings, handles continuous…

Methodology · Statistics 2026-05-19 Peikai Wu , Kuan Sun , Zhiguo Xiao

In this paper, we focus on the problem of integrating Energy-based Models (EBM) as guiding priors for motion optimization. EBMs are a set of neural networks that can represent expressive probability density distributions in terms of a Gibbs…

Robotics · Computer Science 2023-01-13 Julen Urain , An T. Le , Alexander Lambert , Georgia Chalvatzaki , Byron Boots , Jan Peters

Normalization techniques play an important role in supporting efficient and often more effective training of deep neural networks. While conventional methods explicitly normalize the activations, we suggest to add a loss term instead. This…

Machine Learning · Computer Science 2018-11-22 Etai Littwin , Lior Wolf

Existing approaches to predictive uncertainty rely either on multi-hypothesis prediction, which promotes diversity but lacks principled aggregation, or on ensemble learning, which improves accuracy but rarely captures the structured…

Machine Learning · Computer Science 2025-09-04 Alejandro Rodriguez Dominguez , Muhammad Shahzad , Xia Hong

Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016). Tu and Gimpel (2018) developed an efficient framework for energy-based models by training "inference networks" to…

Computation and Language · Computer Science 2020-10-13 Lifu Tu , Richard Yuanzhe Pang , Kevin Gimpel

Deep learning models for human activity recognition (HAR) based on sensor data have been heavily studied recently. However, the generalization ability of deep models on complex real-world HAR data is limited by the availability of…

Computer Vision and Pattern Recognition · Computer Science 2021-06-30 Chenglin Li , Carrie Lu Tong , Di Niu , Bei Jiang , Xiao Zuo , Lei Cheng , Jian Xiong , Jianming Yang

In this paper, we present work in progress on activity recognition and prediction in real homes using either binary sensor data or depth video data. We present our field trial and set-up for collecting and storing the data, our methods, and…

Computer Vision and Pattern Recognition · Computer Science 2019-05-22 Flavia Dias Casagrande , Evi Zouganeli

Machine learning (ML) approaches have shown promising results for predicting molecular properties relevant for chemical process design. However, they are often limited by scarce experimental property data and lack thermodynamic consistency.…

Chemical Physics · Physics 2026-02-23 Jan Pavšek , Alexander Mitsos , Elvis J. Sim , Jan G. Rittig

We develop a new Gibbs sampler for a linear mixed model with a Dirichlet process random effect term, which is easily extended to a generalized linear mixed model with a probit link function. Our Gibbs sampler exploits the properties of the…

Statistics Theory · Mathematics 2010-02-26 Minjung Kyung , Jeff Gill , George Casella

In order to establish the thermodynamic stability of a system, knowledge of its Gibbs free energy is essential. Most often, the Gibbs free energy is predicted within the CALPHAD framework using models employing thermodynamic properties,…

The performance of a neural network for a given task is largely determined by the initial calibration of the network parameters. Yet, it has been shown that the calibration, also referred to as training, is generally NP-complete. This…

Quantum Physics · Physics 2019-11-21 Yidong Liao , Daniel Ebler , Feiyang Liu , Oscar Dahlsten

It is typically understood that the training of modern neural networks is a process of fitting the probability distribution of desired output. However, recent paradoxical observations in a number of language generation tasks let one wonder…

Machine Learning · Computer Science 2023-05-31 Huang Bojun , Fei Yuan

Ionic liquids (ILs) are important solvents for sustainable processes and predicting activity coefficients (ACs) of solutes in ILs is needed. Recently, matrix completion methods (MCMs), transformers, and graph neural networks (GNNs) have…

Machine Learning · Computer Science 2024-01-17 Jan G. Rittig , Karim Ben Hicham , Artur M. Schweidtmann , Manuel Dahmen , Alexander Mitsos

Neural networks often make predictions relying on the spurious correlations from the datasets rather than the intrinsic properties of the task of interest, facing sharp degradation on out-of-distribution (OOD) test data. Existing de-bias…

Machine Learning · Computer Science 2023-01-20 Xinzhe Han , Shuhui Wang , Chi Su , Qingming Huang , Qi Tian

In the context of time-series forecasting, we propose a LSTM-based recurrent neural network architecture and loss function that enhance the stability of the predictions. In particular, the loss function penalizes the model, not only on the…

Signal Processing · Electrical Eng. & Systems 2020-09-09 Maxime De Bois , Mounîm A. El Yacoubi , Mehdi Ammi

Graph Neural Networks (GNNs) became useful for learning on non-Euclidean data. However, their best performance depends on choosing the right model architecture and the training objective, also called the loss function. Researchers have…

Machine Learning · Computer Science 2025-06-18 Khushnood Abbas , Ruizhe Hou , Zhou Wengang , Dong Shi , Niu Ling , Satyaki Nan , Alireza Abbasi

Studies in neuroscience have shown that biological synapses follow a log-normal distribution whose transitioning can be explained by noisy multiplicative dynamics. Biological networks can function stably even under dynamically fluctuating…

Machine Learning · Computer Science 2025-06-24 Keigo Nishida , Eren Mehmet Kıral , Kenichi Bannai , Mohammad Emtiyaz Khan , Thomas Möllenhoff

We propose a neural network-based approach that computes a stable and generalizing metric (LSiM) to compare data from a variety of numerical simulation sources. We focus on scalar time-dependent 2D data that commonly arises from motion and…

Machine Learning · Computer Science 2021-01-29 Georg Kohl , Kiwon Um , Nils Thuerey