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.
Proposes a label propagation framework for domain adaptation.
A susceptibility propagation that is constructed by combining a belief propagation and a linear response method is used for approximate computation for Markov random fields. Herein, we formulate a new, improved susceptibility propagation by using the concept of a diagonal matching method that is based on mean-field app…
New method adapts without backprop, faster and better.
A new method improves label propagation for unsupervised domain adaptation.
Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep …
Decoupled GCN is shown to be equivalent to label propagation.
Unsupervised domain adaptation aiming to learn a specific task for one domain using another domain data has emerged to address the labeling issue in supervised learning, especially because it is difficult to obtain massive amounts of labeled data in practice. The existing methods have succeeded by reducing the differen…
AP-GCN improves graph data processing by dynamically deciding communication steps.
Adapts BP-based algorithms for deep learning, improving performance and accuracy.
Unseen data conditions can inflict serious performance degradation on systems relying on supervised machine learning algorithms. Because data can often be unseen, and because traditional machine learning algorithms are trained in a supervised manner, unsupervised adaptation techniques must be used to adapt the model to…
Defines a calculus for integrating Moreau envelopes in differentiable programming.
Efficient EP algorithm improves smoothing distribution inference in financial models.
Proposes QEP to mitigate quantization error propagation in layer-wise post-training quantization.
Proposes dynamic channel pruning during neural network training.
New method combines Bloom filters and belief propagation for efficient group testing.
We propose an original particle-based implementation of the Loopy Belief Propagation (LPB) algorithm for pairwise Markov Random Fields (MRF) on a continuous state space. The algorithm constructs adaptively efficient proposal distributions approximating the local beliefs at each note of the MRF. This is achieved by cons…
A novel framework for adaptive multi-agent communication in reinforcement learning.
While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the variety of tasks to be solved. In this chapter, we explore how to adapt the Layer-wise Relevance Propagation (LRP) technique used for explain…
Novel methods for splitting Gaussian mixtures improve uncertainty propagation in nonlinear systems.
The Resilient Propagation (Rprop) algorithm has been very popular for backpropagation training of multilayer feed-forward neural networks in various applications. The standard Rprop however encounters difficulties in the context of deep neural networks as typically happens with gradient-based learning algorithms. In th…
Organizations adapt ML models to new data types using existing resources.
Proposes a method to adapt DNNs to drift in data distribution.
EP method speeds up Bayesian probit regression in high dimensions.
We consider the wave equation on a product cone and find a joint asymptotic expansion for solutions near null and future infinities. The rates of decay seen in the expansion at future infinity are the resonances of a hyperbolic cone and were computed by the authors in a previous paper. The expansion treats an asymptoti…
Paper proposes a new method for more accurate group testing of infected patients.
HS-MoE selects sparse experts using adaptive priors and data-adaptive gating.
Dropout has proven to be an effective technique for regularization and preventing the co-adaptation of neurons in deep neural networks (DNN). It randomly drops units with a probability during the training stage of DNN. Dropout also provides a way of approximately combining exponentially many different neural networ…
Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain. In this paper, we present joint adaptation networks (JAN), which learn a transfer network by aligning the joint distributions of multiple domain-specific layers across domai…
New method improves ResNet performance without batch normalization.
We consider the weighted belief-propagation (WBP) decoder recently proposed by Nachmani et al. where different weights are introduced for each Tanner graph edge and optimized using machine learning techniques. Our focus is on simple-scaling models that use the same weights across certain edges to reduce the storage and…
New approach to deeper graph neural networks to avoid performance degradation.
Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to weight initialization strategies often make networks difficult to train, especially when users are experimenting with new architectures. Her…
Algorithm detects causal change points quickly with adaptive interventions.
We introduce a mixed-effects model to learn spatiotempo-ral patterns on a network by considering longitudinal measures distributed on a fixed graph. The data come from repeated observations of subjects at different time points which take the form of measurement maps distributed on a graph such as an image or a mesh. Th…
PushNet efficiently and adaptively pushes messages in neural networks, improving performance.
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks. Specifically, BN depends on batch statistics for layerwise input normalization during training which makes the estimates of …
The study proves rigidity for Poincaré-Einstein manifolds with flat Euclidean conformal infinity.
Study reveals XAI methods fail in neuroimaging, suggesting domain-specific adaptation.
Modeling supply chain disruptions from climate hazards with adaptive firms.
We explore whether useful temporal neural generative models can be learned from sequential data without back-propagation through time. We investigate the viability of a more neurocognitively-grounded approach in the context of unsupervised generative modeling of sequences. Specifically, we build on the concept of predi…
Edge devices adapt pre-trained models to local data without backpropagation.
Proposes IFCDA framework to improve cross-domain adaptation.
The paper proves regularity of states on manifolds with unstable dynamics.
A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapt…
Recently popularized graph neural networks achieve the state-of-the-art accuracy on a number of standard benchmark datasets for graph-based semi-supervised learning, improving significantly over existing approaches. These architectures alternate between a propagation layer that aggregates the hidden states of the local…
Generalized belief propagation converges to optimal solutions on graphs with motifs.
We consider the core reinforcement-learning problem of on-policy value function approximation from a batch of trajectory data, and focus on various issues of Temporal Difference (TD) learning and Monte Carlo (MC) policy evaluation. The two methods are known to achieve complementary bias-variance trade-off properties, w…
We propose a simple yet effective technique to simplify the training and the resulting model of neural networks. In back propagation, only a small subset of the full gradient is computed to update the model parameters. The gradient vectors are sparsified in such a way that only the top-k elements (in terms of magnitude…