Focusing on implicit neural representations, we present a novel in situ training protocol that employs limited memory buffers of full and sketched data samples, where the sketched data are leveraged to prevent catastrophic forgetting. The theoretical motivation for our use of sketching as a regularizer is presented via a simple Johnson-Lindenstrauss-informed result. While our methods may be of wider interest in the field of continual learning, we specifically target in situ neural compression using implicit neural representation-based hypernetworks. We evaluate our method on a variety of complex simulation data in two and three dimensions, over long time horizons, and across unstructured grids and non-Cartesian geometries. On these tasks, we show strong reconstruction performance at high compression rates. Most importantly, we demonstrate that sketching enables the presented in situ scheme to approximately match the performance of the equivalent offline method.

Over the past decades, there has been an explosion in the amount of available Earth Observation (EO) data. The unprecedented coverage of the Earth's surface and atmosphere by satellite imagery has resulted in large volumes of data that must be transmitted to ground stations, stored in data centers, and distributed to end users. Modern Earth System Models (ESMs) face similar challenges, operating at high spatial and temporal resolutions, producing petabytes of data per simulated day. Data compression has gained relevance over the past decade, with neural compression (NC) emerging from deep learning and information theory, making EO data and ESM outputs ideal candidates due to their abundance of unlabeled data. In this review, we outline recent developments in NC applied to geospatial data. We introduce the fundamental concepts of NC including seminal works in its traditional applications to image and video compression domains with focus on lossy compression. We discuss the unique characteristics of EO and ESM data, contrasting them with "natural images", and explain the additional challenges and opportunities they present. Moreover, we review current applications of NC across various EO modalities and explore the limited efforts in ESM compression to date. The advent of self-supervised learning (SSL) and foundation models (FM) has advanced methods to efficiently distill representations from vast unlabeled data. We connect these developments to NC for EO, highlighting the similarities between the two fields and elaborate on the potential of transferring compressed feature representations for machine--to--machine communication. Based on insights drawn from this review, we devise future directions relevant to applications in EO and ESM.

High-energy, large-scale particle colliders in nuclear and high-energy physics generate data at extraordinary rates, reaching up to $1$ terabyte and several petabytes per second, respectively. The development of real-time, high-throughput data compression algorithms capable of reducing this data to manageable sizes for permanent storage is of paramount importance. A unique characteristic of the tracking detector data is the extreme sparsity of particle trajectories in space, with an occupancy rate ranging from approximately $10^{-6}$ to $10\%$. Furthermore, for downstream tasks, a continuous representation of this data is often more useful than a voxel-based, discrete representation due to the inherently continuous nature of the signals involved. To address these challenges, we propose a novel approach using implicit neural representations for data learning and compression. We also introduce an importance sampling technique to accelerate the network training process. Our method is competitive with traditional compression algorithms, such as MGARD, SZ, and ZFP, while offering significant speed-ups and maintaining negligible accuracy loss through our importance sampling strategy.

It is generally well understood that predictive classification and compression are intrinsically related concepts in information theory. Indeed, many deep learning methods are explained as learning a kind of compression, and that better compression leads to better performance. We interrogate this hypothesis via the Normalized Compression Distance (NCD), which explicitly relies on compression as the means of measuring similarity between sequences and thus enables nearest-neighbor classification. By turning popular large language models (LLMs) into lossless compressors, we develop a Neural NCD and compare LLMs to classic general-purpose algorithms like gzip. In doing so, we find that classification accuracy is not predictable by compression rate alone, among other empirical aberrations not predicted by current understanding. Our results imply that our intuition on what it means for a neural network to ``compress'' and what is needed for effective classification are not yet well understood.

This paper presents a family of neural network compression methods of simulated atmospheric states, with the aim of reducing the currently immense storage requirements of such data from cloud scale (petabytes) to desktop scale (terabytes). This need for compression has come about over past 50 years, characterized by a steady push to increase the resolution of atmospheric simulations, increasing the size and storage demands of the resulting datasets (e.g., Neumann et al. (2019), Schneider et al. (2023), Stevens et al. (2024)), while atmospheric simulation has come to play an increasingly critical role in scientific, industrial and policy-level pursuits. Higher spatial resolutions unlock the ability of simulators to deliver more accurate predictions and resolve ever more atmospheric phenomena. For example, while current models often operate at 25 - 50 km resolution, resolving storms requires 1 km resolution (Stevens et al., 2020), while resolving the motion of (and radiative effects due to) low clouds require 100 m resolution (Satoh et al., 2019; Schneider et al., 2017). Machine learning models for weather prediction also face opportunities and challenges with higher resolution: while additional granularity may afford better modeling opportunities, even the present size of atmospheric states poses a significant bottleneck for loading training data and serving model outputs (Chantry et al., 2021). To put the data storage problem in perspective, storing 40 years of reanalysis data from the ECMWF Reanalysis v5 dataset (ERA5, Hersbach et al. (2020)) at full spatial and temporal resolution (i.e.

Neural compression has brought tremendous progress in designing lossy compressors with good rate-distortion (RD) performance at low complexity. Thus far, neural compression design involves transforming the source to a latent vector, which is then rounded to integers and entropy coded. While this approach has been shown to be optimal in a one-shot sense on certain sources, we show that it is highly sub-optimal on i.i.d. sequences, and in fact always recovers scalar quantization of the original source sequence. We demonstrate that the sub-optimality is due to the choice of quantization scheme in the latent space, and not the transform design. By employing lattice quantization instead of scalar quantization in the latent space, we demonstrate that Lattice Transform Coding (LTC) is able to recover optimal vector quantization at various dimensions and approach the asymptotically-achievable rate-distortion function at reasonable complexity. On general vector sources, LTC improves upon standard neural compressors in one-shot coding performance. LTC also enables neural compressors that perform block coding on i.i.d. vector sources, which yields coding gain over optimal one-shot coding.

IoT devices are increasingly the source of data for machine learning (ML) applications running on edge servers. Data transmissions from devices to servers are often over local wireless networks whose bandwidth is not just limited but, more importantly, variable. Furthermore, in cyber-physical systems interacting with the physical environment, image offloading is also commonly subject to timing constraints. It is, therefore, important to develop an adaptive approach that maximizes the inference performance of ML applications under timing constraints and the resource constraints of IoT devices. In this paper, we use image classification as our target application and propose progressive neural compression (PNC) as an efficient solution to this problem. Although neural compression has been used to compress images for different ML applications, existing solutions often produce fixed-size outputs that are unsuitable for timing-constrained offloading over variable bandwidth. To address this limitation, we train a multi-objective rateless autoencoder that optimizes for multiple compression rates via stochastic taildrop to create a compression solution that produces features ordered according to their importance to inference performance. Features are then transmitted in that order based on available bandwidth, with classification ultimately performed using the (sub)set of features received by the deadline. We demonstrate the benefits of PNC over state-of-the-art neural compression approaches and traditional compression methods on a testbed comprising an IoT device and an edge server connected over a wireless network with varying bandwidth.

Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allowing compression algorithms to be learned end-to-end from data using powerful generative models such as normalizing flows, variational autoencoders, diffusion probabilistic models, and generative adversarial networks. The present article aims to introduce this field of research to a broader machine learning audience by reviewing the necessary background in information theory (e.g., entropy coding, rate-distortion theory) and computer vision (e.g., image quality assessment, perceptual metrics), and providing a curated guide through the essential ideas and methods in the literature thus far.

Artificial intelligence (AI) is disrupting a multitude of industries. This article is a response to an article arguing that an AI Winter maybe inevitable. However, I believe that there are fundamental differences between what happened in the 1970s (the fist AI winter) and late 1980s (the second AI winter with the fall of Expert Systems) with the arrival and growth of the internet, smart mobiles and social media resulting in the volume and velocity of data being generated constantly increasing and requiring Machine Learning and Deep Learning to make sense of the Big Data that we generate. For those wishing to see a details about what AI is then I suggest reading an Intro to AI, and for the purposes of this article I will assume Machine Learning and Deep Learning to be a subset of Artificial Intelligence (AI). AI deals with the area of developing computing systems that are capable of performing tasks that humans are very good at, for example recognising objects, recognising and making sense of speech, and decision making in a constrained environment.

This article is a response to an article arguing that an AI Winter maybe inevitable. However, I believe that there are fundamental differences between what happened in the 1970s (the fist AI winter) and late 1980s (the second AI winter with the fall of Expert Systems) with the arrival and growth of the internet, smart mobiles and social media resulting in the volume and velocity of data being generated constantly increasing and requiring Machine Learning and Deep Learning to make sense of the Big Data that we generate. For those wishing to see a details about what AI is then I suggest reading an Intro to AI, and for the purposes of this article I will assume Machine Learning and Deep Learning to be a subset of Artificial Intelligence (AI). AI deals with the area of developing computing systems that are capable of performing tasks that humans are very good at, for example recognising objects, recognising and making sense of speech, and decision making in a constrained environment. The rapid growth in Big Data has driven much of the growth in AI alongside reduced cost of data storage (Cloud Servers) and Graphical Processing Units (GPUs) making Deep Learning more scalable.