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.
New insights into encoder-decoder structures using information measures.
BiPE blends intra-segment and inter-segment encodings for better length extrapolation.
In this paper, we suggest a framework to make use of mutual information as a regularization criterion to train Auto-Encoders (AEs). In the proposed framework, AEs are regularized by minimization of the mutual information between input and encoding variables of AEs during the training phase. In order to estimate the ent…
The key idea of variational auto-encoders (VAEs) resembles that of traditional auto-encoder models in which spatial information is supposed to be explicitly encoded in the latent space. However, the latent variables in VAEs are vectors, which can be interpreted as multiple feature maps of size 1x1. Such representations…
We introduce the Mutual Information Machine (MIM), a probabilistic auto-encoder for learning joint distributions over observations and latent variables. MIM reflects three design principles: 1) low divergence, to encourage the encoder and decoder to learn consistent factorizations of the same underlying distribution; 2…
The condition number predicts efficient information encoding in neural units, aiding model fine-tuning.
Learning an encoding of feature vectors in terms of an over-complete dictionary or a information geometric (Fisher vectors) construct is wide-spread in statistical signal processing and computer vision. In content based information retrieval using deep-learning classifiers, such encodings are learnt on the flattened la…
Paper proposes LCP for structural encodings, outperforming existing methods.
The paper explores how AI systems use information geometry to encode semantic structure.
The choice of sentence encoder architecture reflects assumptions about how a sentence's meaning is composed from its constituent words. We examine the contribution of these architectures by holding them randomly initialised and fixed, effectively treating them as as hand-crafted language priors, and evaluating the resu…
In this paper, we consider recommender systems with side information in the form of graphs. Existing collaborative filtering algorithms mainly utilize only immediate neighborhood information and have a hard time taking advantage of deeper neighborhoods beyond 1-2 hops. The main caveat of exploiting deeper graph informa…
This paper investigates a multi-terminal source coding problem under a logarithmic loss fidelity which does not necessarily lead to an additive distortion measure. The problem is motivated by an extension of the Information Bottleneck method to a multi-source scenario where several encoders have to build cooperatively …
We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework. Our key principles are symmetry and mutual information, where symmetry encourages the encoder and decoder to learn differe…
In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables. These two quantities are complementary and are jointly applied to information behavior…
Enhanced Bayesian target encoding uses sampling techniques to improve model performance.
Improved method for encoding contingency tables reduces mutual information bias.
Conformer encoder reverses sequence in time dimension, affecting decoder training.
A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective is to generalize well to unseen data. Although there is enough numerical eviden…
We present a representation learning framework for financial time series forecasting. One challenge of using deep learning models for finance forecasting is the shortage of available training data when using small datasets. Direct trend classification using deep neural networks trained on small datasets is susceptible …
SplitWise enhances stepwise regression by adaptively encoding numeric predictors into binary features.
New method for Transformer models to encode position information without sequential bias.
In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect of low-level features was reduced in the speaker embedding encoding. Therefore, we propose masked cro…
Neural encoding and decoding, which aim to characterize the relationship between stimuli and brain activities, have emerged as an important area in cognitive neuroscience. Traditional encoding models, which focus on feature extraction and mapping, consider the brain as an input-output mapper without inner states. In th…
Unified MTL framework for heterogeneous data integrates shared and task-specific encoders.
A model learns stock trading rules from raw prices using encoder-decoder neural network.
GATES improves neural architecture search by modeling operations as information transformation.
Statistical models usually require vector representations of categorical variables, using for instance one-hot encoding. This strategy breaks down when the number of categories grows, as it creates high-dimensional feature vectors. Additionally, for string entries, one-hot encoding does not capture information in their…
Learning from multiple sources of information is an important problem in machine-learning research. The key challenges are learning representations and formulating inference methods that take into account the complementarity and redundancy of various information sources. In this paper we formulate a variational autoenc…
Information bottleneck (IB) is a technique for extracting information in one random variable that is relevant for predicting another random variable . IB works by encoding in a compressed "bottleneck" random variable from which can be accurately decoded. However, finding the optimal bottleneck variab…
Meta learning with information theory and Gaussian processes.
Visualizing high-dimensional data is an essential task in Data Science and Machine Learning. The Centroid-Encoder (CE) method is similar to the autoencoder but incorporates label information to keep objects of a class close together in the reduced visualization space. CE exploits nonlinearity and labels to encode high …
Single auto-encoder learns cross-domain image translation.
This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue. We present an attentive dual encoder model that includes an attention mechanism on top of the extracted word-level features from two encoders, one for context and one for label respectively. To improve…
Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data and advanced learning algorithms. The resulting models are considered as intell…
Unified framework analyzes and compares RFF and RoPE PEs for music generation.
Paper proposes Adversarial CCA for multi-view alignment and generation.
This paper will explore the use of autoencoders for semantic hashing in the context of Information Retrieval. This paper will summarize how to efficiently train an autoencoder in order to create meaningful and low-dimensional encodings of data. This paper will demonstrate how computing and storing the closest encodings…
Skull stripping is usually the first step for most brain analysisprocess in magnetic resonance images. A lot of deep learn-ing neural network based methods have been developed toachieve higher accuracy. Since the 3D deep learning modelssuffer from high computational cost and are subject to GPUmemory limit challenge, a …
We introduce the BriarPatch, a pixel-space intervention that obscures sensitive attributes from representations encoded in pre-trained classifiers. The patches encourage internal model representations not to encode sensitive information, which has the effect of pushing downstream predictors towards exhibiting demograph…
Study compares hypergraph and graph-level models for higher-order relational learning.
Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is an inherent disadvantage of recurrent neural network structure, and disregarding relationship between source words during encoding step. Wher…
Encoding a sequence of observations is an essential task with many applications. The encoding can become highly efficient when the observations are generated by a dynamical system. A dynamical system imposes regularities on the observations that can be leveraged to achieve a more efficient code. We propose a method to …
BinConv improves time series forecasting by preserving ordinal information in a classification framework.
New method decomposes sensory information from neurons into specific stimuli and features.
BF-VAE estimates uncertainty from LF and HF QoI samples.
Non-negative tensor factorization models enable predictive analysis on count data. Among them, Bayesian Poisson-Gamma models can derive full posterior distributions of latent factors and are less sensitive to sparse count data. However, current inference methods for these Bayesian models adopt restricted update rules f…
Unified framework connects credit risk metrics with information theory.
Decodes neural activity to detect context effects in natural settings.