A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Residual networks with block width max(d_x, d_y) approximate all functions.
Residual flows are shown to approximate MMD well.
Enhanced image denoising with MWRDCNN using residual dense blocks.
AANets balance stability and plasticity in CIL.
JKO-iFlow uses neural ODEs to improve generative models with reduced memory and training complexity.
Recent results in the literature indicate that a residual network (ResNet) composed of a single residual block outperforms linear predictors, in the sense that all local minima in its optimization landscape are at least as good as the best linear predictor. However, these results are limited to a single residual block …
Residual networks (ResNets) are a deep learning architecture that substantially improved the state of the art performance in certain supervised learning tasks. Since then, they have received continuously growing attention. ResNets have a recursive structure where is a neural network cal…
Batch normalization makes deep residual networks train faster.
Improved ResNets and DenseNets models for better feature reuse.
We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In exp…
Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood. Invertible residual networks provide a flexible family of transformations where only Lipschitz conditions rather than strict architectural constraints are needed for enforci…
Study provides selective inference method for latent block models.
CN-SBM clusters cancer samples and regions based on copy number variants.
In this effort, we propose a new deep architecture utilizing residual blocks inspired by implicit discretization schemes. As opposed to the standard feed-forward networks, the outputs of the proposed implicit residual blocks are defined as the fixed points of the appropriately chosen nonlinear transformations. We show …
We conduct mathematical analysis on the effect of batch normalization (BN) on gradient backpropogation in residual network training, which is believed to play a critical role in addressing the gradient vanishing/explosion problem, in this work. By analyzing the mean and variance behavior of the input and the gradient i…
We present the Video Ladder Network (VLN) for efficiently generating future video frames. VLN is a neural encoder-decoder model augmented at all layers by both recurrent and feedforward lateral connections. At each layer, these connections form a lateral recurrent residual block, where the feedforward connection repres…
Accelerating Speculative Diffusions via Block Verification
Deep learning has shown promising results on many machine learning tasks but DL models are often complex networks with large number of neurons and layers, and recently, complex layer structures known as building blocks. Finding the best deep model requires a combination of finding both the right architecture and the co…
Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account. We investigate the generalized notion of frames designed with image properties in mind, as alternatives to this parametrization. We show that frame-based ResNets and De…
Sharp stability threshold found for deep residual architectures.
Recently, with convolutional neural networks gaining significant achievements in many challenging machine learning fields, hand-crafted neural networks no longer satisfy our requirements as designing a network will cost a lot, and automatically generating architectures has attracted increasingly more attention and focu…
Due to the success of residual networks (resnets) and related architectures, shortcut connections have quickly become standard tools for building convolutional neural networks. The explanations in the literature for the apparent effectiveness of shortcuts are varied and often contradictory. We hypothesize that shortcut…
Simultaneous orthogonal matching pursuit (SOMP) and block OMP (BOMP) are two widely used techniques for sparse support recovery in multiple measurement vector (MMV) and block sparse (BS) models respectively. For optimal performance, both SOMP and BOMP require \textit{a priori} knowledge of signal sparsity or noise vari…
This paper studies deep learning methodologies for portfolio optimization in the US equities market. We present a novel residual switching network that can automatically sense changes in market regimes and switch between momentum and reversal predictors accordingly. The residual switching network architecture combines …
Effective theory for Transformer initialization improves model performance.
Unified learning-rate scale for CNNs and ResNets, avoiding depth imbalance.
Tractable yet expressive density estimators are a key building block of probabilistic machine learning. While sum-product networks (SPNs) offer attractive inference capabilities, obtaining structures large enough to fit complex, high-dimensional data has proven challenging. In this paper, we present random sum-product …
Modern methods for learning over graph input data have shown the fruitfulness of accounting for relationships among elements in a collection. However, most methods that learn over set input data use only rudimentary approaches to exploit intra-collection relationships. In this work we introduce Deep Message Passing on …
Study tests how U.S. equity prices align with global asset frequencies using financial variables.
In many video coding systems, separable transforms (such as two-dimensional DCT-2) have been used to code block residual signals obtained after prediction. This paper proposes a parametric approach to build graph-based separable transforms (GBSTs) for video coding. Specifically, a GBST is derived from a pair of line gr…
We present in this paper a model for forecasting short-term power loads based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers' understanding of the task by virtue of different neural network building blocks. Specifically, a modified deep residual network is formulated…
Extends VAEs to handle complex Bayesian network structures.
RDL-Net improves speech enhancement with fewer parameters and better performance.
Extended LSTM improves language modeling performance.
ImpFlows generalize normalizing flows by implicitly defining transformations.
ResNets promote smoother interpolations than MLPs, enhancing generalization.
DiffusionBlocks trains neural networks by breaking them into independent blocks, reducing memory usage.
Image super-resolution is a challenging task and has attracted increasing attention in research and industrial communities. In this paper, we propose a novel end-to-end Attention-based DenseNet with Residual Deconvolution named as ADRD. In our ADRD, a weighted dense block, in which the current layer receives weighted f…
Nonnegative matrix factorization (NMF) has attracted much attention in the last decade as a dimension reduction method in many applications. Due to the explosion in the size of data, naturally the samples are collected and stored distributively in local computational nodes. Thus, there is a growing need to develop algo…
RFRBoost uses random features to boost deep residual neural networks, improving performance and computational efficiency.
We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation. Typically, enforcing invertibility requires partitioning dimensions or restricting network architectures. In contrast, our approach only requires adding a simple …
We study the stability and convergence of training deep ResNets with gradient descent. Specifically, we show that the parametric branch in the residual block should be scaled down by a factor to guarantee stable forward/backward process, where is the number of residual blocks. Moreover, we establi…
Signal models based on sparsity, low-rank and other properties have been exploited for image reconstruction from limited and corrupted data in medical imaging and other computational imaging applications. In particular, sparsifying transform models have shown promise in various applications, and offer numerous advantag…
Paper models graph edge dependencies using latent variables for community detection.
PSiLON Net uses weight normalization and 1-path-norm regularization for efficient learning and sparsity.
Unified algorithm solves convex optimization problems with optimal rates.
HaKAN uses Hahn-KAN blocks to forecast multivariate time series.
Recent several years have witnessed the surge of asynchronous (async-) parallel computing methods due to the extremely big data involved in many modern applications and also the advancement of multi-core machines and computer clusters. In optimization, most works about async-parallel methods are on unconstrained proble…