In-sensor computing, which integrates computation directly within the sensor, has emerged as a promising paradigm for machine vision applications such as AR/VR and smart home systems. By processing data on-chip before transmission, it alleviates the bandwidth bottleneck caused by high-resolution, high-frame-rate image transmission, particularly in video applications. We envision a system architecture that integrates a CMOS image sensor (CIS) with a logic chip via advanced packaging, where the logic chip processes early-stage deep neural network (DNN) layers. However, its limited compute and memory make deploying advanced DNNs challenging. A simple solution is to split the model, executing the first part on the logic chip and the rest off-chip. However, modern DNNs require multiple layers before dimensionality reduction, limiting their ability to achieve the primary goal of in-sensor computing: minimizing data bandwidth. To address this, we propose a dual-branch autoencoder-based vision architecture that deploys a lightweight encoder on the logic chip while the task-specific network runs off-chip. The encoder is trained using a triple loss function: (1) task-specific loss to optimize accuracy, (2) entropy loss to enforce compact and compressible representations, and (3) reconstruction loss (mean-square error) to preserve essential visual information. This design enables a four-order-of-magnitude reduction in output activation dimensionality compared to input images, resulting in a $2{-}4.5\times$ decrease in energy consumption, as validated by our hardware-backed semi-analytical energy models. We evaluate our approach on CNN and ViT-based models across applications in smart home and augmented reality domains, achieving state-of-the-art accuracy with energy efficiency of up to 22.7 TOPS/W.
We propose an online learning framework for forecasting nonlinear spatio-temporal signals (fields). The method integrates (i) dimensionality reduction, here, a simple proper orthogonal decomposition (POD) projection; (ii) a generalized autoregressive model to forecast reduced dynamics, here, a reservoir computer; (iii) online adaptation to update the reservoir computer (the model), here, ensemble sequential data assimilation.We demonstrate the framework on a wake past a cylinder governed by the Navier-Stokes equations, exploring the assimilation of full flow fields (projected onto POD modes) and sparse sensors. Three scenarios are examined: a na\"ive physical state estimation; a two-fold estimation of physical and reservoir states; and a three-fold estimation that also adjusts the model parameters. The two-fold strategy significantly improves ensemble convergence and reduces reconstruction error compared to the na\"ive approach. The three-fold approach enables robust online training of partially-trained reservoir computers, overcoming limitations of a priori training. By unifying data-driven reduced order modelling with Bayesian data assimilation, this work opens new opportunities for scalable online model learning for nonlinear time series forecasting.
This paper presents a novel theoretical framework for reducing the computational complexity of multi-model adaptive control/estimation systems through systematic transformation to controllable canonical form. While traditional multi-model approaches face exponential growth in computational demands with increasing system dimension, we introduce a parameter-tying theorem that enables significant dimension reduction through careful analysis of system characteristics in canonical form. The approach leverages monotonicity properties and coordinated parameter relationships to establish minimal sets of identification models while preserving system stability and performance. We develop rigorous criteria for verifying plant inclusion within the convex hull of identification models and derive weight transformation relationships that maintain system properties across coordinate transformations. The effectiveness of the framework is demonstrated through application to coupled lateral-roll vehicle dynamics, where the dimension reduction enables real-time implementation while maintaining estimation accuracy. The results show that the proposed transformation approach can achieve comparable performance to conventional methods while requiring substantially fewer identification models, enabling practical deployment in high-dimensional systems.
This study proposes a computationally efficient method for optimizing multi-zone thermostatically controlled loads (TCLs) by leveraging dimensionality reduction through an auto-encoder. We develop a multi-task learning framework to jointly represent latent variables and formulate a state-space model based on observed TCL operation data. This significantly reduces the dimensionality of TCL variables and states while preserving critical nonlinear interdependencies in TCL control. To address various application scenarios, we introduce optimization algorithms based on system identification (OptIden) and system simulation (OptSim) tailored to the latent variable representation. These approaches employ automatic differentiation and zeroth-order techniques, respectively, for efficient implementation. We evaluate the proposed method using a 90-zone apartment prototype, comparing its performance to traditional high-dimensional optimization. Results demonstrate that our approach effectively reduces control costs while achieving significantly higher computational efficiency.
Bayesian formulations of inverse problems are attractive for their ability to incorporate prior knowledge and update probabilistic models as new data become available. Markov chain Monte Carlo (MCMC) methods sample posterior probability density functions (pdfs) but require accurate prior models and many likelihood evaluations. Dimensionality-reduction methods, such as principal component analysis (PCA), can help define the prior and train surrogate models that efficiently approximate costly forward solvers. However, for problems like full waveform inversion, the complex input/output relations often cannot be captured well by surrogate models trained only on prior samples, leading to biased results. Including samples from high-posterior-probability regions can improve accuracy, but these regions are hard to identify in advance. We propose an iterative method that progressively refines the surrogate model. Starting with low-frequency data, we train an initial surrogate and perform an MCMC inversion. The resulting posterior samples are then used to retrain the surrogate, allowing us to expand the frequency bandwidth in the next inversion step. Repeating this process reduces model errors and improves the surrogate's accuracy over the relevant input domain. Ultimately, we obtain a highly accurate surrogate across the full bandwidth, enabling a final MCMC inversion. Numerical results from 2D synthetic crosshole Ground Penetrating Radar (GPR) examples show that our method outperforms ray-based approaches and those relying solely on prior sampling. The overall computational cost is reduced by about two orders of magnitude compared to full finite-difference time-domain modeling.
The Xeno-Canto bird audio repository is an invaluable resource for those interested in vocalizations and other sounds made by birds around the world. This is particularly the case for machine learning researchers attempting to improve on the bird species recognition accuracy of classification models. However, the task of extracting labeled datasets from the recordings found in this crowd-sourced repository faces several challenges. One challenge of particular significance to machine learning practitioners is that one bird species label is applied to each audio recording, but frequently other sounds are also captured including other bird species, other animal sounds, anthropogenic and other ambient sounds. These non-target bird species sounds can result in dataset labeling discrepancies referred to as label noise. In this work we present a cleaning process consisting of audio preprocessing followed by dimensionality reduction and unsupervised outlier detection (UOD) to reduce the label noise in a dataset derived from Xeno-Canto recordings. We investigate three neural network dimensionality reduction techniques: two flavors of convolutional autoencoders and variational deep embedding (VaDE (Jiang, 2017)). While both methods show some degree of effectiveness at detecting outliers for most bird species datasets, we found significant variation in the performance of the methods from one species to the next. We believe that the results of this investigation demonstrate that the application of our cleaning process can meaningfully reduce the label noise of bird species datasets derived from Xeno-Canto audio repository but results vary across species.
Accurate prediction of FIFA World Cup match outcomes holds significant value for analysts, coaches, bettors, and fans. This paper presents a machine learning framework specifically designed to forecast match winners in FIFA World Cup. By integrating both team-level historical data and player-specific performance metrics such as goals, assists, passing accuracy, and tackles, we capture nuanced interactions often overlooked by traditional aggregate models. Our methodology processes multi-year data to create year-specific team profiles that account for evolving rosters and player development. We employ classification techniques complemented by dimensionality reduction and hyperparameter optimization, to yield robust predictive models. Experimental results on data from the FIFA 2022 World Cup demonstrate our approach's superior accuracy compared to baseline method. Our findings highlight the importance of incorporating individual player attributes and team-level composition to enhance predictive performance, offering new insights into player synergy, strategic match-ups, and tournament progression scenarios. This work underscores the transformative potential of rich, player-centric data in sports analytics, setting a foundation for future exploration of advanced learning architectures such as graph neural networks to model complex team interactions.
We aim to approximate a continuously differentiable function $u:\mathbb{R}^d \rightarrow \mathbb{R}$ by a composition of functions $f\circ g$ where $g:\mathbb{R}^d \rightarrow \mathbb{R}^m$, $m\leq d$, and $f : \mathbb{R}^m \rightarrow \mathbb{R}$ are built in a two stage procedure. For a fixed $g$, we build $f$ using classical regression methods, involving evaluations of $u$. Recent works proposed to build a nonlinear $g$ by minimizing a loss function $\mathcal{J}(g)$ derived from Poincar\'e inequalities on manifolds, involving evaluations of the gradient of $u$. A problem is that minimizing $\mathcal{J}$ may be a challenging task. Hence in this work, we introduce new convex surrogates to $\mathcal{J}$. Leveraging concentration inequalities, we provide sub-optimality results for a class of functions $g$, including polynomials, and a wide class of input probability measures. We investigate performances on different benchmarks for various training sample sizes. We show that our approach outperforms standard iterative methods for minimizing the training Poincar\'e inequality based loss, often resulting in better approximation errors, especially for rather small training sets and $m=1$.
As the field of representation learning grows, there has been a proliferation of different loss functions to solve different classes of problems. We introduce a single information-theoretic equation that generalizes a large collection of modern loss functions in machine learning. In particular, we introduce a framework that shows that several broad classes of machine learning methods are precisely minimizing an integrated KL divergence between two conditional distributions: the supervisory and learned representations. This viewpoint exposes a hidden information geometry underlying clustering, spectral methods, dimensionality reduction, contrastive learning, and supervised learning. This framework enables the development of new loss functions by combining successful techniques from across the literature. We not only present a wide array of proofs, connecting over 23 different approaches, but we also leverage these theoretical results to create state-of-the-art unsupervised image classifiers that achieve a +8% improvement over the prior state-of-the-art on unsupervised classification on ImageNet-1K. We also demonstrate that I-Con can be used to derive principled debiasing methods which improve contrastive representation learners.
Exosomes are small vesicles crucial for cell signaling and disease biomarkers. Due to their complexity, an "omics" approach is preferable to individual biomarkers. While Raman spectroscopy is effective for exosome analysis, it requires high sample concentrations and has limited sensitivity to lipids and proteins. Surface-enhanced Raman spectroscopy helps overcome these challenges. In this study, we leverage Neo4j graph databases to organize 3,045 Raman spectra of exosomes, enhancing data generalization. To further refine spectral analysis, we introduce a novel spectral filtering process that integrates the PageRank Filter with optimal Dimensionality Reduction. This method improves feature selection, resulting in superior classification performance. Specifically, the Extra Trees model, using our spectral processing approach, achieves 0.76 and 0.857 accuracy in classifying hyperglycemic, hypoglycemic, and normal exosome samples based on Raman spectra and surface, respectively, with group 10-fold cross-validation. Our results show that graph-based spectral filtering combined with optimal dimensionality reduction significantly improves classification accuracy by reducing noise while preserving key biomarker signals. This novel framework enhances Raman-based exosome analysis, expanding its potential for biomedical applications, disease diagnostics, and biomarker discovery.
The lack of generalization in learning-based autonomous driving applications is shown by the narrow range of road scenarios that vehicles can currently cover. A generalizable approach should capture many distinct road structures and topologies, as well as consider traffic participants, and dynamic changes in the environment, so that vehicles can navigate and perform motion planning tasks even in the most difficult situations. Designing suitable feature spaces for neural network-based motion planers that encapsulate all kinds of road scenarios is still an open research challenge. This paper tackles this learning-based generalization challenge and shows how graph representations of road networks can be leveraged by using multidimensional scaling (MDS) techniques in order to obtain such feature spaces. State-of-the-art graph representations and MDS approaches are analyzed for the autonomous driving use case. Finally, the option of embedding graph nodes is discussed in order to perform easier learning procedures and obtain dimensionality reduction.
Retrieval-Augmented Generation enhances language models by retrieving relevant information from external knowledge bases, relying on high-dimensional vector embeddings typically stored in float32 precision. However, storing these embeddings at scale presents significant memory challenges. To address this issue, we systematically investigate on MTEB benchmark two complementary optimization strategies: quantization, evaluating standard formats (float16, int8, binary) and low-bit floating-point types (float8), and dimensionality reduction, assessing methods like PCA, Kernel PCA, UMAP, Random Projections and Autoencoders. Our results show that float8 quantization achieves a 4x storage reduction with minimal performance degradation (<0.3%), significantly outperforming int8 quantization at the same compression level, being simpler to implement. PCA emerges as the most effective dimensionality reduction technique. Crucially, combining moderate PCA (e.g., retaining 50% dimensions) with float8 quantization offers an excellent trade-off, achieving 8x total compression with less performance impact than using int8 alone (which provides only 4x compression). To facilitate practical application, we propose a methodology based on visualizing the performance-storage trade-off space to identify the optimal configuration that maximizes performance within their specific memory constraints.
High-dimensional vector embeddings are widely used in retrieval systems, yet dimensionality reduction (DR) is seldom applied due to its tendency to distort nearest-neighbor (NN) structure critical for search. Existing DR techniques such as PCA and UMAP optimize global or manifold-preserving criteria, rather than retrieval-specific objectives. We present MPAD: Maximum Pairwise Absolute Difference, an unsupervised DR method that explicitly preserves approximate NN relations by maximizing the margin between k-NNs and non-k-NNs under a soft orthogonality constraint. This design enables MPAD to retain ANN-relevant geometry without supervision or changes to the original embedding model. Experiments across multiple domains show that MPAD consistently outperforms standard DR methods in preserving neighborhood structure, enabling more accurate search in reduced dimensions.
The continuous monitoring of the interactions between cyber-physical components of any industrial control system (ICS) is required to secure automation of the system controls, and to guarantee plant processes are fail-safe and remain in an acceptably safe state. Safety is achieved by managing actuation (where electric signals are used to trigger physical movement), dependent on corresponding sensor readings; used as ground truth in decision making. Timely detection of anomalies (attacks, faults and unascertained states) in ICSs is crucial for the safe running of a plant, the safety of its personnel, and for the safe provision of any services provided. We propose an anomaly detection method that involves accurate linearization of the non-linear forms arising from sensor-actuator(s) relationships, primarily because solving linear models is easier and well understood. Further, the time complexity of the anomaly detection scenario/problem at hand is lowered using dimensionality reduction of the actuator(s) in relationship with a sensor. We accomplish this by using a well-known water treatment testbed as a use case. Our experiments show millisecond time response to detect anomalies and provide explainability; that are not simultaneously achieved by other state of the art AI/ML models with eXplainable AI (XAI) used for the same purpose. Further, we pin-point the sensor(s) and its actuation state for which anomaly was detected.
Solar flares are among the most powerful and dynamic events in the solar system, resulting from the sudden release of magnetic energy stored in the Sun's atmosphere. These energetic bursts of electromagnetic radiation can release up to 10^32 erg of energy, impacting space weather and posing risks to technological infrastructure and therefore require accurate forecasting of solar flare occurrences and intensities. This study evaluates the predictive performance of three machine learning algorithms: Random Forest, k-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost) for classifying solar flares into 4 categories (B, C, M, X). Using the dataset of 13 SHARP parameters, the effectiveness of the models was evaluated in binary and multiclass classification tasks. The analysis utilized 8 principal components (PC), capturing 95% of data variance, and 100 PCs, capturing 97.5% of variance. Our approach uniquely combines binary and multiclass classification with different levels of dimensionality reduction, an innovative methodology not previously explored in the context of solar flare prediction. Employing a 10-fold stratified cross-validation and grid search for hyperparameter tuning ensured robust model evaluation. Our findings indicate that Random Forest and XGBoost consistently demonstrate strong performance across all metrics, benefiting significantly from increased dimensionality. The insights of this study enhance future research by optimizing dimensionality reduction techniques and informing model selection for astrophysical tasks. By integrating this newly acquired knowledge into future research, more accurate space weather forecasting systems can be developed, along with a deeper understanding of solar physics.
The goal of this paper is to show how different machine learning tools on the Riemannian manifold $\mathcal{P}_d$ of Symmetric Positive Definite (SPD) matrices can be united under a probabilistic framework. For this, we will need several Gaussian distributions defined on $\mathcal{P}_d$. We will show how popular classifiers on $\mathcal{P}_d$ can be reinterpreted as Bayes Classifiers using these Gaussian distributions. These distributions will also be used for outlier detection and dimension reduction. By showing that those distributions are pervasive in the tools used on $\mathcal{P}_d$, we allow for other machine learning tools to be extended to $\mathcal{P}_d$.
We propose a generalization of modern representation learning objectives by reframing them as recursive divergence alignment processes over localized conditional distributions While recent frameworks like Information Contrastive Learning I-Con unify multiple learning paradigms through KL divergence between fixed neighborhood conditionals we argue this view underplays a crucial recursive structure inherent in the learning process. We introduce Recursive KL Divergence Optimization RKDO a dynamic formalism where representation learning is framed as the evolution of KL divergences across data neighborhoods. This formulation captures contrastive clustering and dimensionality reduction methods as static slices while offering a new path to model stability and local adaptation. Our experiments demonstrate that RKDO offers dual efficiency advantages approximately 30 percent lower loss values compared to static approaches across three different datasets and 60 to 80 percent reduction in computational resources needed to achieve comparable results. This suggests that RKDOs recursive updating mechanism provides a fundamentally more efficient optimization landscape for representation learning with significant implications for resource constrained applications.
Dimensionality reduction techniques are fundamental for analyzing and visualizing high-dimensional data. With established methods like t-SNE and PCA presenting a trade-off between representational power and interpretability. This paper introduces a novel approach that bridges this gap by combining the interpretability of linear methods with the expressiveness of non-linear transformations. The proposed algorithm constructs a non-linear mapping between high-dimensional and low-dimensional spaces through a combination of linear transformations, each weighted by Gaussian functions. This architecture enables complex non-linear transformations while preserving the interpretability advantages of linear methods, as each transformation can be analyzed independently. The resulting model provides both powerful dimensionality reduction and transparent insights into the transformed space. Techniques for interpreting the learned transformations are presented, including methods for identifying suppressed dimensions and how space is expanded and contracted. These tools enable practitioners to understand how the algorithm preserves and modifies geometric relationships during dimensionality reduction. To ensure the practical utility of this algorithm, the creation of user-friendly software packages is emphasized, facilitating its adoption in both academia and industry.
The rapid evolution of Internet of Things (IoT) technology has led to a significant increase in the number of IoT devices, applications, and services. This surge in IoT devices, along with their widespread presence, has made them a prime target for various cyber-attacks, particularly through IoT botnets. As a result, security has become a major concern within the IoT ecosystem. This study focuses on investigating how the latent dimension impacts the performance of different deep learning classifiers when trained on latent vector representations of the train dataset. The primary objective is to compare the outcomes of these models when encoder components from two cutting-edge architectures: the Vision Transformer (ViT) and the Variational Auto-Encoder (VAE) are utilized to project the high dimensional train dataset to the learned low dimensional latent space. The encoder components are employed to project high-dimensional structured .csv IoT botnet traffic datasets to various latent sizes. Evaluated on N-BaIoT and CICIoT2022 datasets, findings reveal that VAE-encoder based dimension reduction outperforms ViT-encoder based dimension reduction for both datasets in terms of four performance metrics including accuracy, precision, recall, and F1-score for all models which can be attributed to absence of spatial patterns in the datasets the ViT model attempts to learn and extract from image instances.
Ensuring fairness in machine learning is a critical and challenging task, as biased data representations often lead to unfair predictions. To address this, we propose Deep Fair Learning, a framework that integrates nonlinear sufficient dimension reduction with deep learning to construct fair and informative representations. By introducing a novel penalty term during fine-tuning, our method enforces conditional independence between sensitive attributes and learned representations, addressing bias at its source while preserving predictive performance. Unlike prior methods, it supports diverse sensitive attributes, including continuous, discrete, binary, or multi-group types. Experiments on various types of data structure show that our approach achieves a superior balance between fairness and utility, significantly outperforming state-of-the-art baselines.