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.
Exemplar VAEs link generative models with nearest neighbor retrieval and data augmentation.
Proposes a framework for generating explainable AI exemplars.
EASE optimizes exemplar selection for ICL in LLMs efficiently.
Efficiently preserves old class knowledge in memory-limited settings.
We propose a framework for synthesis of geological images based on an exemplar image. We synthesize new realizations such that the discrepancy in the patch distribution between the realizations and the exemplar image is minimized. Such discrepancy is quantified using a kernel method for two-sample test called maximum m…
Paper proposes mnemonics framework for MCIL without forgetting.
This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs). ExGANs are a type of conditional GAN that utilize exemplar information to produce high-quality, personalized in painting results. We propos…
ADER addresses continual learning in session-based recommendation by periodically replaying exemplars with adaptive distillation.
A method for collecting human supervision that combines rules and instance labels.
Exemplar-based clustering methods have been shown to produce state-of-the-art results on a number of synthetic and real-world clustering problems. They are appealing because they offer computational benefits over latent-mean models and can handle arbitrary pairwise similarity measures between data points. However, when…
We present a generative framework for generalized zero-shot learning where the training and test classes are not necessarily disjoint. Built upon a variational autoencoder based architecture, consisting of a probabilistic encoder and a probabilistic conditional decoder, our model can generate novel exemplars from seen/…
In this paper, we consider the problem of selecting representatives from a data set for arbitrary supervised/unsupervised learning tasks. We identify a subset of a data set such that 1) the size of is much smaller than and 2) efficiently describes the entire data set, in a way formalized via convex …
Metric learning methods for dimensionality reduction in combination with k-Nearest Neighbors (kNN) have been extensively deployed in many classification, data embedding, and information retrieval applications. However, most of these approaches involve pairwise training data comparisons, and thus have quadratic computat…
Explicit high-order feature interactions efficiently capture essential structural knowledge about the data of interest and have been used for constructing generative models. We present a supervised discriminative High-Order Parametric Embedding (HOPE) approach to data visualization and compression. Compared to deep emb…
With the growing interest on Network Analysis, Relational Data Mining is becoming an emphasized domain of Data Mining. This paper addresses the problem of extracting representative elements from a relational dataset. After defining the notion of degree of representativeness, computed using the Borda aggregation procedu…
For a certain class of distributions, we prove that the linear programming relaxation of -medoids clustering---a variant of -means clustering where means are replaced by exemplars from within the dataset---distinguishes points drawn from nonoverlapping balls with high probability once the number of points drawn a…
LoRA- improves EFCL by stabilizing feature drifts.
This article examines five common misunderstandings about case-study research: (1) Theoretical knowledge is more valuable than practical knowledge; (2) One cannot generalize from a single case, therefore the single case study cannot contribute to scientific development; (3) The case study is most useful for generating …
In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs. Compared with VAEs, f-VAEs generate more vivid images, solved the blurred-image problem of VAEs. Compared with flow-based models such as Glow, f-VAE is more lightweight and converges faster, achieving the same performance und…
Neural network models that are not conditioned on class identities were shown to facilitate knowledge transfer between classes and to be well-suited for one-shot learning tasks. Following this motivation, we further explore and establish such models and present a novel neural network architecture for the task of weakly…
Over the last few decades, psychologists have developed sophisticated formal models of human categorization using simple artificial stimuli. In this paper, we use modern machine learning methods to extend this work into the realm of naturalistic stimuli, enabling human categorization to be studied over the complex visu…
People belong to multiple communities, words belong to multiple topics, and books cover multiple genres; overlapping clusters are commonplace. Many existing overlapping clustering methods model each person (or word, or book) as a non-negative weighted combination of "exemplars" who belong solely to one community, with …
Many natural signals exhibit a sparse representation, whenever a suitable describing model is given. Here, a linear generative model is considered, where many sparsity-based signal processing techniques rely on such a simplified model. As this model is often unknown for many classes of the signals, we need to select su…
This work tackles posterior collapse in conditional and hierarchical VAEs.
BS-VAE separates decoder variance and beta to improve VAE performance.
A tutorial on VAEs explaining its derivation and applications.
BayesAdapter turns pre-trained NNs into reliable BNNs with minimal overhead.
New system for i-vector speaker recognition based on variational autoencoder (VAE) is investigated. VAE is a promising approach for developing accurate deep nonlinear generative models of complex data. Experiments show that VAE provides speaker embedding and can be effectively trained in an unsupervised manner. LLR est…
The paper provides convergence guarantees for VAEs using SGD and Adam.
VAEs help in learning latent variables for cryo-EM applications.
PRI-VAE learns disentangled representations by optimizing principle-of-relevant-information.
CVAE learns disentangled and coupled representations without prior knowledge.
Variational autoencoders (VAEs) have ushered in a new era of unsupervised learning methods for complex distributions. Although these techniques are elegant in their approach, they are typically not useful for representation learning. In this work, we propose a simple yet powerful class of VAEs that simultaneously resul…
NE-VAE prevents posterior collapse in VAEs by embedding neighbors in latent space.
The variational autoencoder (VAE) framework remains a popular option for training unsupervised generative models, especially for discrete data where generative adversarial networks (GANs) require workaround to create gradient for the generator. In our work modeling US postal addresses, we show that our discrete VAE wit…
q-VAE extracts disentangled latent spaces for robot control and dynamic systems.
Single training run learns optimal VAE parameters for various β values.
VAEs analyzed using harmonic analysis, showing how variance controls frequency content and robustness.
SKR-VAE improves VAEs for ICA with reduced computational cost.
VAE improves anomaly detection for jet tagging at the LHC.
High-dimensional VAEs inevitably collapse to prior, requiring large datasets for good performance.
NeRF-VAE generates 3D scenes with geometric structure from few images.
Flexible VAEs using FIFs improve model likelihood on image datasets.
Improved deep hierarchical VAE with diffusion-based VampPrior.
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…
As a general-purpose generative model architecture, VAE has been widely used in the field of image and natural language processing. VAE maps high dimensional sample data into continuous latent variables with unsupervised learning. Sampling in the latent variable space of the feature, VAE can construct new image or text…
The VAE's reconstruction ability is studied using PAC-Bayes theory.
HL-VAE extends VAE for heterogeneous temporal and longitudinal data.