The continuously growing amount of seismic data collected worldwide is outpacing our abilities for analysis, since to date, such datasets have been analyzed in a human-expert-intensive, supervised ...fashion. Moreover, analyses that are conducted can be strongly biased by the standard models employed by seismologists. In response to both of these challenges, we develop a new unsupervised machine learning framework for detecting and clustering seismic signals in continuous seismic records. Our approach combines a deep scattering network and a Gaussian mixture model to cluster seismic signal segments and detect novel structures. To illustrate the power of the framework, we analyze seismic data acquired during the June 2017 Nuugaatsiaq, Greenland landslide. We demonstrate the blind detection and recovery of the repeating precursory seismicity that was recorded before the main landslide rupture, which suggests that our approach could lead to more informative forecasting of the seismic activity in seismogenic areas.
We develop new theoretical results on matrix perturbation to shed light on the impact of architecture on the performance of a deep network. In particular, we explain analytically what deep learning ...practitioners have long observed empirically: the parameters of some deep architectures (e.g., residual networks, ResNets, and Dense networks, DenseNets) are easier to optimize than others (e.g., convolutional networks, ConvNets). Building on our earlier work connecting deep networks with continuous piecewise-affine splines, we develop an exact local linear representation of a deep network layer for a family of modern deep networks that includes ConvNets at one end of a spectrum and ResNets, DenseNets, and other networks with skip connections at the other. For regression and classification tasks that optimize the squared-error loss, we show that the optimization loss surface of a modern deep network is piecewise quadratic in the parameters, with local shape governed by the singular values of a matrix that is a function of the local linear representation. We develop new perturbation results for how the singular values of matrices of this sort behave as we add a fraction of the identity and multiply by certain diagonal matrices. A direct application of our perturbation results explains analytically why a network with skip connections (such as a ResNet or DenseNet) is easier to optimize than a ConvNet: thanks to its more stable singular values and smaller condition number, the local loss surface of such a network is less erratic, less eccentric, and features local minima that are more accommodating to gradient-based optimization. Our results also shed new light on the impact of different nonlinear activation functions on a deep network’s singular values, regardless of its architecture.
We build a rigorous bridge between deep networks (DNs) and approximation theory via spline functions and operators. Our key result is that a large class of DNs can be written as a composition of ...max-affine spline operators (MASOs) that provide a powerful portal through which we view and analyze their inner workings. For instance, conditioned on the spline partition region containing the input signal, the output of an MASO DN can be written as a simple affine transformation of the input. This implies that a DN constructs a set of signal-dependent, class-specific templates against which the signal is compared via a simple inner product; we explore the links to the classical theory of optimal classification via matched filters and the effects of data memorization. Going further, we propose a simple penalty term that can be added to the cost function of any DN learning algorithm to force the templates to be orthogonal with each other; this leads to significantly improved classification performance and reduced overfitting with no change to the DN architecture. The spline partition of the input signal space that is implicitly induced by an MASO directly links DNs to the theory of vector quantization (VQ) and K-means clustering, which opens up new geometric avenues to study how DNs organize signals in a hierarchical fashion. To validate the utility of the VQ interpretation, we develop and validate a new distance metric for signals and images that quantify the difference between their VQ encodings.
Deep Neural Networks (DNNs) outshine alternative function approximators in many settings thanks to their modularity in composing any desired differentiable operator. The formed parametrized ...functional is then tuned to solve a task at hand from simple gradient descent. This modularity comes at the cost of making strict enforcement of constraints on DNNs, e.g. from a priori knowledge of the task, or from desired physical properties, an open challenge. In this paper we propose the first provable affine constraint enforcement method for DNNs that only requires minimal changes into a given DNN's forward-pass, that is computationally friendly, and that leaves the optimization of the DNN's parameter to be unconstrained, i.e. standard gradient-based method can be employed. Our method does not require any sampling and provably ensures that the DNN fulfills the affine constraint on a given input space's region at any point during training, and testing. We coin this method POLICE, standing for Provably Optimal LInear Constraint Enforcement. Github: https://github.com/RandallBalestriero/POLICE
One fruitful formulation of Deep Networks (DNs) enabling their theoretical study and providing practical guidelines to practitioners relies on Piecewise Affine Splines. In that realm, a DN's ...input-mapping is expressed as per-region affine map-ping where those regions are implicitly determined by the model's architecture and form a partition of their input space. That partition -which is involved in all the results spanned from this line of research- has so far only been computed on 2/3-dimensional slices of the DN's input space or estimated by random sampling. In this paper, we provide the first parallel algorithm that does exact enumeration of the DN's partition regions. The proposed algorithm enables one to finally assess the closeness of the commonly employed approximations methods, e.g. based on random sampling of the DN input space. One of our key finding is that if one is only interested in regions with "large" volume, then uniform sampling of the space is highly efficient, but that if one is also interested in discovering the "small" regions of the partition, then uniform sampling is exponentially costly with the DN's input space dimension. On the other hand, our proposed method has complexity scaling linearly with input dimension and the number of regions.
We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of any pre-trained deep generative network (DGN). Leveraging the fact ...that DGNs are, or can be ap-proximated by, continuous piecewise affine splines, we derive the analytical DGN output space distribution as a function of the product of the DGN's Jacobian singular values raised to a power p. We dub p the polarity param-eter and prove that p focuses the DGN sampling on the modes (p < 0) or anti-modes (p > 0) of the DGN output-space probability distribution. We demonstrate that nonzero polarity values achieve a better precision-recall (quality-diversity) Pareto frontier than standard methods, such as truncation, for a number of state-of-the-art DGNs. We also present quantitative and qualitative results on the improve-ment of overall generation quality (e.g., in terms of the Fréchet Inception Distance) for a number of state-of-the-art DGNs, including StyleGAN3, BigGAN-deep, NVAE, for different conditional and unconditional image generation tasks. In particular, Polarity Sampling redefines the state-of-the-art for StyleGAN2 on the FFHQ Dataset to FID 2.57, StyleGAN2 on the LSUN Car Dataset to FID 2.27 and Style-GAN3 on the AFHQv2 Dataset to FID 3.95. Colab Demo.
On Minimal Variations for Unsupervised Representation Learning Cabannes, Vivien; Bietti, Alberto; Balestriero, Randall
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
2023-June-4
Conference Proceeding
Open access
Unsupervised representation learning aims at describing raw data efficiently to solve various downstream tasks. It has been approached with many techniques, such as manifold learning, diffusion maps, ...or more recently self-supervised learning. Those techniques are arguably all based on the underlying assumption that target functions, associated with future downstream tasks, have low variations in densely populated regions of the input space. Our main contribution is to unveil minimal variations as a guiding principle behind unsupervised representation learning paves the way to better practical guidelines for self-supervised learning algorithms.
Acoustic monitoring is used to study marine mammals in oceans. Automated analysis for captured sound is almost essential because of the large quantity of data. The deep learning approach is an ...efficient method, however acoustic features are often not adapted. Convolutional Neural Net can be seen as an optimal kernel decomposition, nevertheless it requires large amount of training data to learn its kernels. An alternative using pre-imposed kernels and thus not requiring any amount of data is the scattering framework which imposes as kernels wavelet filters. Our research focuses on adaptive time-frequency decomposition of bioacoustic signal, based on cubic spline learning representation. We give the theoretical derivations of the model, and demonstrates efficient real applications of various signal, including chirps of songs of Blue Whale.
Universal Frame Thresholding Cosentino, Romain; Balestriero, Randall; Baraniuk, Richard G. ...
IEEE signal processing letters,
2020, Volume:
27
Journal Article
Peer reviewed
Open access
We provide the first frame agnostic thresholding scheme based on risk minimization, which can be applied to arbitrary frames and provide its theoretical guarantees. We investigate the proposed ...scheme, study its empirical risk, and demonstrates how it falls back to the standard Donoho thresholding scheme for orthogonal basis. We then validate our technique and apply it to the overcomplete wavelet transforms of the Deep Scattering Network. We are thus obtaining an invariant and thresholded representation of the signals providing significant performance gains compared to the non-thresholded version.
Abstract The continuously growing amount of seismic data collected worldwide is outpacing our abilities for analysis, since to date, such datasets have been analyzed in a human-expert-intensive, ...supervised fashion. Moreover, analyses that are conducted can be strongly biased by the standard models employed by seismologists. In response to both of these challenges, we develop a new unsupervised machine learning framework for detecting and clustering seismic signals in continuous seismic records. Our approach combines a deep scattering network and a Gaussian mixture model to cluster seismic signal segments and detect novel structures. To illustrate the power of the framework, we analyze seismic data acquired during the June 2017 Nuugaatsiaq, Greenland landslide. We demonstrate the blind detection and recovery of the repeating precursory seismicity that was recorded before the main landslide rupture, which suggests that our approach could lead to more informative forecasting of the seismic activity in seismogenic areas.