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.
CAggNet improves medical image segmentation by fusing coarse and fine features.
In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways. The re-designed skip pathways aim at r…
We consider the problem of undirected graphical model inference. In many applications, instead of perfectly recovering the unknown graph structure, a more realistic goal is to infer some graph invariants (e.g., the maximum degree, the number of connected subgraphs, the number of isolated nodes). In this paper, we propo…
Paper analyzes the free energy of CNNs with skip connections in Bayesian learning.
The paper proves skip connections help neural networks avoid shallow local minima.
Skip connections are an essential component of current state-of-the-art deep neural networks (DNNs) such as ResNet, WideResNet, DenseNet, and ResNeXt. Despite their huge success in building deeper and more powerful DNNs, we identify a surprising security weakness of skip connections in this paper. Use of skip connectio…
New insights into GNN optimization reveal skip connections and depth accelerate training.
This paper examines how skip connections prevent rank collapse in sequence models.
This work analyzes how bottleneck layers and skip connections affect linear denoising autoencoders' generalization.
DenseNets introduce concatenation-type skip connections that achieve state-of-the-art accuracy in several computer vision tasks. In this paper, we reveal that the topology of the concatenation-type skip connections is closely related to the gradient propagation which, in turn, enables a predictable behavior of DNNs' te…
DARTS- improves robustness by factoring out skip connections' advantage.
Theory explains why DARTS favors deep architectures over shallow ones.
Study on autoencoder denoising in high dimensions.
This paper explains GCNs using NTKs and improves their performance.
We show that the skip-gram formulation of word2vec trained with negative sampling is equivalent to a weighted logistic PCA. This connection allows us to better understand the objective, compare it to other word embedding methods, and extend it to higher dimensional models.
Backpropagation is the workhorse of deep learning, however, several other biologically-motivated learning rules have been introduced, such as random feedback alignment and difference target propagation. None of these methods have produced a competitive performance against backpropagation. In this paper, we show that bi…
In this work, we extend the SchNet architecture by using weighted skip connections to assemble the final representation. This enables us to study the relative importance of each interaction block for property prediction. We demonstrate on both the QM9 and MD17 dataset that their relative weighting depends strongly on t…
A long-standing obstacle to progress in deep learning is the problem of vanishing and exploding gradients. Although, the problem has largely been overcome via carefully constructed initializations and batch normalization, architectures incorporating skip-connections such as highway and resnets perform much better than …
Variational autoencoders learn distributions of high-dimensional data. They model data with a deep latent-variable model and then fit the model by maximizing a lower bound of the log marginal likelihood. VAEs can capture complex distributions, but they can also suffer from an issue known as "latent variable collapse," …
We introduce a novel approach, requiring only mild assumptions, for the characterization of deep neural networks at initialization. Our approach applies both to fully-connected and convolutional networks and easily incorporates batch normalization and skip-connections. Our key insight is to consider the evolution with …
We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While nesting sub-models layer-wise is straight-forward with deep-supervision as proposed in \cite{xie2015holistically}, channel-wise nesting has…
Proposes PSCs for UQ in deep nets without retraining.
Theoretical limits of deep residual networks show consistent covariance structures.
Paper studies ResNet dynamics using NTH, reducing width requirement.
Self-supervised skip-tree training improves mathematical reasoning in language models.
TabSODA improves imputation of surveys with skips and ordinal data.
The behavior of the gradient descent (GD) algorithm is analyzed for a deep neural network model with skip-connections. It is proved that in the over-parametrized regime, for a suitable initialization, with high probability GD can find a global minimum exponentially fast. Generalization error estimates along the GD path…
While enormous progress has been made to Variational Autoencoder (VAE) in recent years, similar to other deep networks, VAE with deep networks suffers from the problem of degeneration, which seriously weakens the correlation between the input and the corresponding latent codes, deviating from the goal of the representa…
While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing works exploited this observation by learning to skip convolutional layers in an input-dependent manner. However, we argue their binary deci…
OSA overcomes instability in skipless Transformers.
Boost-and-Skip generates minority samples without guidance, faster and more effectively.
Wide CNNs outperform infinite width networks, revealing scaling laws.
We introduce the notion of a nested open book, a submanifold equipped with an open book structure compatible with an ambient open book, and describe in detail the special case of a push-off of the binding of an open book. This enables us to explicitly describe a natural open book decomposition of a fibre connected sum …
New framework explains deep learning using signal processing techniques.
Federated Learning aims to train distributed deep models without sharing the raw data with the centralized server. Similarly, in distributed inference of neural networks, by partitioning the network and distributing it across several physical nodes, activations and gradients are exchanged between physical nodes, rather…
Random feature maps improve forecasting of chaotic dynamical systems.
We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time. The model represents words and contexts by latent trajectories in an embedding space. At each moment in time, the embedding vectors are inferred from a probabilistic version of word2ve…
Corrected CBOW performs similarly to Skip-gram.
Since the invention of word2vec, the skip-gram model has significantly advanced the research of network embedding, such as the recent emergence of the DeepWalk, LINE, PTE, and node2vec approaches. In this work, we show that all of the aforementioned models with negative sampling can be unified into the matrix factoriza…
To discover powerful yet compact models is an important goal of neural architecture search. Previous two-stage one-shot approaches are limited by search space with a fixed depth. It seems handy to include an additional skip connection in the search space to make depths variable. However, it creates a large range of per…
Currently, Markov-Gibbs random field (MGRF) image models which include high-order interactions are almost always built by modelling responses of a stack of local linear filters. Actual interaction structure is specified implicitly by the filter coefficients. In contrast, we learn an explicit high-order MGRF structure b…
PAM models generate dependent random distributions across groups with overlapping clusters.
New framework explains deep neural networks using variational spline theory.
Deep Heaviside networks are limited but can be improved with connections or linear neurons.
Enhances financial risk quantification in classical models.
We propose Dirichlet Simplex Nest, a class of probabilistic models suitable for a variety of data types, and develop fast and provably accurate inference algorithms by accounting for the model's convex geometry and low dimensional simplicial structure. By exploiting the connection to Voronoi tessellation and properties…
New neural architectures with multivariate nonlinearities are optimal in function space.
This work connects IRL methods from ML and economics.