Developing environmentally sustainable refrigerants is critical for mitigating the impact of anthropogenic greenhouse gases on global warming. This study presents a predictive modeling framework to estimate the 100-year global warming potential (GWP 100) of single-component refrigerants using a fully connected neural network implemented on the Multi-Sigma platform. Molecular descriptors from RDKit, Mordred, and alvaDesc were utilized to capture various chemical features. The RDKit-based model achieved the best performance, with a Root Mean Square Error (RMSE) of 481.9 and an R2 score of 0.918, demonstrating superior predictive accuracy and generalizability. Dimensionality reduction through Principal Component Analysis (PCA) and quantile transformation were applied to address the high-dimensional and skewed nature of the dataset,enhancing model stability and performance. Factor analysis identified vital molecular features, including molecular weight, lipophilicity, and functional groups, such as nitriles and allylic oxides, as significant contributors to GWP values. These insights provide actionable guidance for designing environmentally sustainable refrigerants. Integrating RDKit descriptors with Multi-Sigma's framework, which includes PCA, quantile transformation, and neural networks, provides a scalable solution for the rapid virtual screening of low-GWP refrigerants. This approach can potentially accelerate the identification of eco-friendly alternatives, directly contributing to climate mitigation by enabling the design of next-generation refrigerants aligned with global sustainability objectives.
We propose a pair of completely data-driven algorithms for unsupervised classification and dimension reduction, and we empirically study their performance on a number of data sets, both simulated data in three-dimensions and images from the COIL-20 data set. The algorithms take as input a set of points sampled from a uniform distribution supported on a metric space, the latter embedded in an ambient metric space, and they output a clustering or reduction of dimension of the data. They work by constructing a natural family of graphs from the data and selecting the graph which maximizes the relative von Neumann entropy of certain normalized heat operators constructed from the graphs. Once the appropriate graph is selected, the eigenvectors of the graph Laplacian may be used to reduce the dimension of the data, and clusters in the data may be identified with the kernel of the associated graph Laplacian. Notably, these algorithms do not require information about the size of a neighborhood or the desired number of clusters as input, in contrast to popular algorithms such as $k$-means, and even more modern spectral methods such as Laplacian eigenmaps, among others. In our computational experiments, our clustering algorithm outperforms $k$-means clustering on data sets with non-trivial geometry and topology, in particular data whose clusters are not concentrated around a specific point, and our dimension reduction algorithm is shown to work well in several simple examples.
Feature selection is important for high-dimensional data analysis and is non-trivial in unsupervised learning problems such as dimensionality reduction and clustering. The goal of unsupervised feature selection is finding a subset of features such that the data points from different clusters are well separated. This paper presents a novel method called K-means Derived Unsupervised Feature Selection (K-means UFS). Unlike most existing spectral analysis based unsupervised feature selection methods, we select features using the objective of K-means. We develop an alternating direction method of multipliers (ADMM) to solve the NP-hard optimization problem of our K-means UFS model. Extensive experiments on real datasets show that our K-means UFS is more effective than the baselines in selecting features for clustering.
Anomaly detection is a well-established field in machine learning, identifying observations that deviate from typical patterns. The principles of anomaly detection could enhance our understanding of how biological systems recognize and respond to atypical environmental inputs. However, this approach has received limited attention in analyses of cellular and physiological circuits. This study builds on machine learning techniques -- such as dimensionality reduction, boosted decision trees, and anomaly classification -- to develop a conceptual framework for biological circuits. One problem is that machine learning circuits tend to be unrealistically large for use by cellular and physiological systems. I therefore focus on minimal circuits inspired by machine learning concepts, reduced to cellular scale. Through illustrative models, I demonstrate that small circuits can provide useful classification of anomalies. The analysis also shows how principles from machine learning -- such as temporal and atemporal anomaly detection, multivariate signal integration, and hierarchical decision-making cascades -- can inform hypotheses about the design and evolution of cellular circuits. This interdisciplinary approach enhances our understanding of cellular circuits and highlights the universal nature of computational strategies across biological and artificial systems.
Parametric dimensionality reduction methods have gained prominence for their ability to generalize to unseen datasets, an advantage that traditional approaches typically lack. Despite their growing popularity, there remains a prevalent misconception among practitioners about the equivalence in performance between parametric and non-parametric methods. Here, we show that these methods are not equivalent -- parametric methods retain global structure but lose significant local details. To explain this, we provide evidence that parameterized approaches lack the ability to repulse negative pairs, and the choice of loss function also has an impact. Addressing these issues, we developed a new parametric method, ParamRepulsor, that incorporates Hard Negative Mining and a loss function that applies a strong repulsive force. This new method achieves state-of-the-art performance on local structure preservation for parametric methods without sacrificing the fidelity of global structural representation. Our code is available at https://github.com/hyhuang00/ParamRepulsor.
We present FAST-Splat for fast, ambiguity-free semantic Gaussian Splatting, which seeks to address the main limitations of existing semantic Gaussian Splatting methods, namely: slow training and rendering speeds; high memory usage; and ambiguous semantic object localization. In deriving FAST-Splat , we formulate open-vocabulary semantic Gaussian Splatting as the problem of extending closed-set semantic distillation to the open-set (open-vocabulary) setting, enabling FAST-Splat to provide precise semantic object localization results, even when prompted with ambiguous user-provided natural-language queries. Further, by exploiting the explicit form of the Gaussian Splatting scene representation to the fullest extent, FAST-Splat retains the remarkable training and rendering speeds of Gaussian Splatting. Specifically, while existing semantic Gaussian Splatting methods distill semantics into a separate neural field or utilize neural models for dimensionality reduction, FAST-Splat directly augments each Gaussian with specific semantic codes, preserving the training, rendering, and memory-usage advantages of Gaussian Splatting over neural field methods. These Gaussian-specific semantic codes, together with a hash-table, enable semantic similarity to be measured with open-vocabulary user prompts and further enable FAST-Splat to respond with unambiguous semantic object labels and 3D masks, unlike prior methods. In experiments, we demonstrate that FAST-Splat is 4x to 6x faster to train with a 13x faster data pre-processing step, achieves between 18x to 75x faster rendering speeds, and requires about 3x smaller GPU memory, compared to the best-competing semantic Gaussian Splatting methods. Further, FAST-Splat achieves relatively similar or better semantic segmentation performance compared to existing methods. After the review period, we will provide links to the project website and the codebase.
Traits are patterns of brain signals and behaviors that are stable over time but differ across individuals, whereas states are phasic patterns that vary over time, are influenced by the environment, yet oscillate around the traits. The quality of a social interaction depends on the traits and states of the interacting agents. However, it remains unclear how to decipher both traits and states from the same set of brain signals. To explore the hidden neural traits and states in relation to the behavioral ones during social interactions, we developed a pipeline to extract latent dimensions of the brain from electroencephalogram (EEG) data collected during a team flow task. Our pipeline involved two stages of dimensionality reduction: first, non-negative matrix factorization (NMF), followed by linear discriminant analysis (LDA). This pipeline resulted in an interpretable, seven-dimensional EEG latent space that revealed a trait-state hierarchical structure, with macro-segregation capturing neural traits and micro-segregation capturing neural states. Out of the seven latent dimensions, we found that three that significantly contributed to variations across individuals and task states. Using representational similarity analysis, we mapped the EEG latent space to a skill-cognition space, establishing a connection between hidden neural signatures and social interaction behaviors. Our method demonstrates the feasibility of representing both traits and states within a single model that correlates with changes in social behavior.
Drawing motivation from the manifold hypothesis, which posits that most high-dimensional data lies on or near low-dimensional manifolds, we apply manifold learning to the space of neural networks. We learn manifolds where datapoints are neural networks by introducing a distance between the hidden layer representations of the neural networks. These distances are then fed to the non-linear dimensionality reduction algorithm PHATE to create a manifold of neural networks. We characterize this manifold using features of the representation, including class separation, hierarchical cluster structure, spectral entropy, and topological structure. Our analysis reveals that high-performing networks cluster together in the manifold, displaying consistent embedding patterns across all these features. Finally, we demonstrate the utility of this approach for guiding hyperparameter optimization and neural architecture search by sampling from the manifold.
We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that finds a low-dimensional separation-preserving projection of the input data. Our method gives a non-spherical analog of the classical dimension reduction, based on singular value decomposition, that forms a key component of the celebrated spherical clustering algorithm of Vempala and Wang [VW04] (in addition to several other applications). As applications, we obtain an algorithm to (1) cluster an arbitrary total-variation separated mixture of $k$ centered (i.e., zero-mean) Gaussians with $n\geq \operatorname{poly}(d) f(w_{\min}^{-1})$ samples and $\operatorname{poly}(n)$ time, and (2) cluster an arbitrary total-variation separated mixture of $k$ Gaussians with identical but arbitrary unknown covariance with $n \geq d^{O(\log w_{\min}^{-1})} f(w_{\min}^{-1})$ samples and $n^{O(\log w_{\min}^{-1})}$ time. Here, $w_{\min}$ is the minimum mixing weight of the input mixture, and $f$ does not depend on the dimension $d$. Our algorithms naturally extend to tolerating a dimension-independent fraction of arbitrary outliers. Before this work, the techniques in the state-of-the-art non-spherical clustering algorithms needed $d^{O(k)} f(w_{\min}^{-1})$ time and samples for clustering such mixtures. Our results may come as a surprise in the context of the $d^{\Omega(k)}$ statistical query lower bound [DKS17] for clustering non-spherical Gaussian mixtures. While this result is usually thought to rule out $d^{o(k)}$ cost algorithms for the problem, our results show that the lower bounds can in fact be circumvented for a remarkably general class of Gaussian mixtures.
We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error. We provide an in-depth error analysis and proofs of the optimality in minimizing lower bounds of STRESS. We demonstrate Neuc-MDS's ability to address limitations of classical MDS raised by prior research, and test it on various synthetic and real-world datasets in comparison with both linear and non-linear dimension reduction methods.
Network Intrusion Detection (NID) remains a key area of research within the information security community, while also being relevant to Machine Learning (ML) practitioners. The latter generally aim to detect attacks using network features, which have been extracted from raw network data typically using dimensionality reduction methods, such as principal component analysis (PCA). However, PCA is not able to assess the relevance of features for the task at hand. Consequently, the features available are of varying quality, with some being entirely non-informative. From this, two major drawbacks arise. Firstly, trained and deployed models have to process large amounts of unnecessary data, therefore draining potentially costly resources. Secondly, the noise caused by the presence of irrelevant features can, in some cases, impede a model's ability to detect an attack. In order to deal with these challenges, we present Feature Selection for Network Intrusion Detection (FSNID) a novel information-theoretic method that facilitates the exclusion of non-informative features when detecting network intrusions. The proposed method is based on function approximation using a neural network, which enables a version of our approach that incorporates a recurrent layer. Consequently, this version uniquely enables the integration of temporal dependencies. Through an extensive set of experiments, we demonstrate that the proposed method selects a significantly reduced feature set, while maintaining NID performance. Code will be made available upon publication.
This study presents a framework for predicting unsteady transonic wing pressure distributions, integrating an autoencoder architecture with graph convolutional networks and graph-based temporal layers to model time dependencies. The framework compresses high-dimensional pressure distribution data into a lower-dimensional latent space using an autoencoder, ensuring efficient data representation while preserving essential features. Within this latent space, graph-based temporal layers are employed to predict future wing pressures based on past data, effectively capturing temporal dependencies and improving predictive accuracy. This combined approach leverages the strengths of autoencoders for dimensionality reduction, graph convolutional networks for handling unstructured grid data, and temporal layers for modeling time-based sequences. The effectiveness of the proposed framework is validated through its application to the Benchmark Super Critical Wing test case, achieving accuracy comparable to computational fluid dynamics, while significantly reducing prediction time. This framework offers a scalable, computationally efficient solution for the aerodynamic analysis of unsteady phenomena.
Topic modeling, or more broadly, dimensionality reduction, techniques provide powerful tools for uncovering patterns in large datasets and are widely applied across various domains. We investigate how Non-negative Matrix Factorization (NMF) can introduce bias in the representation of data groups, such as those defined by demographics or protected attributes. We present an approach, called Fairer-NMF, that seeks to minimize the maximum reconstruction loss for different groups relative to their size and intrinsic complexity. Further, we present two algorithms for solving this problem. The first is an alternating minimization (AM) scheme and the second is a multiplicative updates (MU) scheme which demonstrates a reduced computational time compared to AM while still achieving similar performance. Lastly, we present numerical experiments on synthetic and real datasets to evaluate the overall performance and trade-offs of Fairer-NMF
Computing expected information gain (EIG) from prior to posterior (equivalently, mutual information between candidate observations and model parameters or other quantities of interest) is a fundamental challenge in Bayesian optimal experimental design. We formulate flexible transport-based schemes for EIG estimation in general nonlinear/non-Gaussian settings, compatible with both standard and implicit Bayesian models. These schemes are representative of two-stage methods for estimating or bounding EIG using marginal and conditional density estimates. In this setting, we analyze the optimal allocation of samples between training (density estimation) and approximation of the outer prior expectation. We show that with this optimal sample allocation, the MSE of the resulting EIG estimator converges more quickly than that of a standard nested Monte Carlo scheme. We then address the estimation of EIG in high dimensions, by deriving gradient-based upper bounds on the mutual information lost by projecting the parameters and/or observations to lower-dimensional subspaces. Minimizing these upper bounds yields projectors and hence low-dimensional EIG approximations that outperform approximations obtained via other linear dimension reduction schemes. Numerical experiments on a PDE-constrained Bayesian inverse problem also illustrate a favorable trade-off between dimension truncation and the modeling of non-Gaussianity, when estimating EIG from finite samples in high dimensions.
While machine-learned models are now routinely employed to facilitate astronomical inquiry, model inputs tend to be limited to a primary data source (namely images or time series) and, in the more advanced approaches, some metadata. Yet with the growing use of wide-field, multiplexed observational resources, individual sources of interest often have a broad range of observational modes available. Here we construct an astronomical multimodal dataset and propose AstroM$^3$, a self-supervised pre-training approach that enables a model to learn from multiple modalities simultaneously. Specifically, we extend the CLIP (Contrastive Language-Image Pretraining) model to a trimodal setting, allowing the integration of time-series photometry data, spectra, and astrophysical metadata. In a fine-tuning supervised setting, our results demonstrate that CLIP pre-training improves classification performance for time-series photometry, where accuracy increases from 84.6% to 91.5%. Furthermore, CLIP boosts classification accuracy by up to 12.6% when the availability of labeled data is limited, showing the effectiveness of leveraging larger corpora of unlabeled data. In addition to fine-tuned classification, we can use the trained model in other downstream tasks that are not explicitly contemplated during the construction of the self-supervised model. In particular we show the efficacy of using the learned embeddings for misclassifications identification, similarity search, and anomaly detection. One surprising highlight is the "rediscovery" of Mira subtypes and two Rotational variable subclasses using manifold learning and dimension reduction algorithm. To our knowledge this is the first construction of an $n>2$ mode model in astronomy. Extensions to $n>3$ modes is naturally anticipated with this approach.
As a powerful tool for characterizing cellular subpopulations and cellular heterogeneity, single cell RNA sequencing (scRNA-seq) technology offers advantages of high throughput and multidimensional analysis. However, the process of data acquisition is often constrained by high cost and limited sample availability. To overcome these limitations, we propose a hybrid model based on Diffusion model and White-Box transformer that aims to generate synthetic and biologically plausible scRNA-seq data. Diffusion model progressively introduce noise into the data and then recover the original data through a denoising process, a forward and reverse process that is particularly suitable for generating complex data distributions. White-Box transformer is a deep learning architecture that emphasizes mathematical interpretability. By minimizing the encoding rate of the data and maximizing the sparsity of the representation, it not only reduces the computational burden, but also provides clear insight into underlying structure. Our White-Box Diffusion Transformer combines the generative capabilities of Diffusion model with the mathematical interpretability of White-Box transformer. Through experiments using six different single-cell RNA-Seq datasets, we visualize both generated and real data using t-SNE dimensionality reduction technique, as well as quantify similarity between generated and real data using various metrics to demonstrate comparable performance of White-Box Diffusion Transformer and Diffusion Transformer in generating scRNA-seq data alongside significant improvements in training efficiency and resource utilization. Our code is available at https://github.com/lingximamo/White-Box-Diffusion-Transformer
Back propagation (BP) is the default solution for gradient computation in neural network training. However, implementing BP-based training on various edge devices such as FPGA, microcontrollers (MCUs), and analog computing platforms face multiple major challenges, such as the lack of hardware resources, long time-to-market, and dramatic errors in a low-precision setting. This paper presents a simple BP-free training scheme on an MCU, which makes edge training hardware design as easy as inference hardware design. We adopt a quantized zeroth-order method to estimate the gradients of quantized model parameters, which can overcome the error of a straight-through estimator in a low-precision BP scheme. We further employ a few dimension reduction methods (e.g., node perturbation, sparse training) to improve the convergence of zeroth-order training. Experiment results show that our BP-free training achieves comparable performance as BP-based training on adapting a pre-trained image classifier to various corrupted data on resource-constrained edge devices (e.g., an MCU with 1024-KB SRAM for dense full-model training, or an MCU with 256-KB SRAM for sparse training). This method is most suitable for application scenarios where memory cost and time-to-market are the major concerns, but longer latency can be tolerated.
We develop a Functional Augmented Vector Autoregression (FunVAR) model to explicitly incorporate firm-level heterogeneity observed in more than one dimension and study its interaction with aggregate macroeconomic fluctuations. Our methodology employs dimensionality reduction techniques for tensor data objects to approximate the joint distribution of firm-level characteristics. More broadly, our framework can be used for assessing predictions from structural models that account for micro-level heterogeneity observed on multiple dimensions. Leveraging firm-level data from the Compustat database, we use the FunVAR model to analyze the propagation of total factor productivity (TFP) shocks, examining their impact on both macroeconomic aggregates and the cross-sectional distribution of capital and labor across firms.
Understanding the global organization of complicated and high dimensional data is of primary interest for many branches of applied sciences. It is typically achieved by applying dimensionality reduction techniques mapping the considered data into lower dimensional space. This family of methods, while preserving local structures and features, often misses the global structure of the dataset. Clustering techniques are another class of methods operating on the data in the ambient space. They group together points that are similar according to a fixed similarity criteria, however unlike dimensionality reduction techniques, they do not provide information about the global organization of the data. Leveraging ideas from Topological Data Analysis, in this paper we provide an additional layer on the output of any clustering algorithm. Such data structure, ClusterGraph, provides information about the global layout of clusters, obtained from the considered clustering algorithm. Appropriate measures are provided to assess the quality and usefulness of the obtained representation. Subsequently the ClusterGraph, possibly with an appropriate structure--preserving simplification, can be visualized and used in synergy with state of the art exploratory data analysis techniques.
This study utilizes machine learning algorithms to analyze and organize knowledge in the field of algorithmic trading. By filtering a dataset of 136 million research papers, we identified 14,342 relevant articles published between 1956 and Q1 2020. We compare traditional practices-such as keyword-based algorithms and embedding techniques-with state-of-the-art topic modeling methods that employ dimensionality reduction and clustering. This comparison allows us to assess the popularity and evolution of different approaches and themes within algorithmic trading. We demonstrate the usefulness of Natural Language Processing (NLP) in the automatic extraction of knowledge, highlighting the new possibilities created by the latest iterations of Large Language Models (LLMs) like ChatGPT. The rationale for focusing on this topic stems from our analysis, which reveals that research articles on algorithmic trading are increasing at a faster rate than the overall number of publications. While stocks and main indices comprise more than half of all assets considered, certain asset classes, such as cryptocurrencies, exhibit a much stronger growth trend. Machine learning models have become the most popular methods in recent years. The study demonstrates the efficacy of LLMs in refining datasets and addressing intricate questions about the analyzed articles, such as comparing the efficiency of different models. Our research shows that by decomposing tasks into smaller components and incorporating reasoning steps, we can effectively tackle complex questions supported by case analyses. This approach contributes to a deeper understanding of algorithmic trading methodologies and underscores the potential of advanced NLP techniques in literature reviews.