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.
Joint diffusion models improve data representation for both generation and prediction.
Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the hidden variables, while the higher layers model the hidden distribution prior. Bu…
Deep structured-prediction energy-based models combine the expressive power of learned representations and the ability of embedding knowledge about the task at hand into the system. A common way to learn parameters of such models consists in a multistage procedure where different combinations of components are trained …
JoCoR improves deep learning with noisy labels by reducing network diversity.
Joint training improves model accuracy by selectively using privileged information.
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We…
Estimates joint causal effects using single-variable interventions on nonlinear models.
FJS method improves multinomial classification accuracy.
This work gives an in-depth derivation of the trainable evidence lower bound obtained from the marginal joint log-Likelihood with the goal of training a Multi-Modal Variational Autoencoder (MVAE).
Jointly tuning ensemble models improves performance and uncertainty calibration.
Multi-task learning is a method for improving the generalizability of multiple tasks. In order to perform multiple classification tasks with one neural network model, the losses of each task should be combined. Previous studies have mostly focused on multiple prediction tasks using joint loss with static weights for tr…
Develops a framework to quantify uncertainties in multiple ML models.
Paper develops a theory explaining contrastive pre-training for multimodal AI.
Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that can process and relate information from these modalities. However, existing work l…
A broad range of cross--domain generation researches boil down to matching a joint distribution by deep generative models (DGMs). Hitherto algorithms excel in pairwise domains while as increases, remain struggling to scale themselves to fit a joint distribution. In this paper, we propose a domain-scalable DGM, i…
We extend recent work (Brehmer, et. al., 2018) that use neural networks as surrogate models for likelihood-free inference. As in the previous work, we exploit the fact that the joint likelihood ratio and joint score, conditioned on both observed and latent variables, can often be extracted from an implicit generative m…
We provide a distribution-free test that can be used to determine whether any two joint distributions and are statistically different by inspection of a large enough set of samples. Following recent efforts from Long et al. [1], we rely on joint kernel distribution embedding to extend the kernel two-sample test…
A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains). This is achieved by learning to sample from conditional dist…
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…
Novel approach trains ASR models with less supervision using bilevel optimization.
We introduce a new method for training deep Boltzmann machines jointly. Prior methods require an initial learning pass that trains the deep Boltzmann machine greedily, one layer at a time, or do not perform well on classifi- cation tasks.
FreST Loss decorrelates spatio-temporal dependencies in graph signals.
Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insuf…
TensorGuide improves LoRA efficiency and expressivity through joint tensor-train optimization.
New federated learning framework reduces model complexity and improves performance.
New method certifies joint adversarial robustness of model ensembles.
Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance de…
Proposes a new method for handling domain shift in samples with biases in both covariates and labels.
Generative model for joint discrete distributions using randomized assignment flows.
AR-CSM models use derivatives of univariate log-conditionals to estimate joint distributions efficiently.
In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifte…
EPINET improves neural networks with less computation.
We introduce a multimodal visual-textual search refinement method for fashion garments. Existing search engines do not enable intuitive, interactive, refinement of retrieved results based on the properties of a particular product. We propose a method to retrieve similar items, based on a query item image and textual re…
We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. Recently, some studies handle multiple modalities on deep generative models, such as variational autoencoders (VAEs). However, these models typically assume that…
Probabilistic linear discriminant analysis (PLDA) is a method used for biometric problems like speaker or face recognition that models the variability of the samples using two latent variables, one that depends on the class of the sample and another one that is assumed independent across samples and models the within-c…
Directed latent variable models that formulate the joint distribution as have the advantage of fast and exact sampling. However, these models have the weakness of needing to specify , often with a simple fixed prior that limits the expressiveness of the model. Undirected latent variabl…
This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm for training Boltzmann Machines. Similar in spirit to the Hessian-Free method of Martens [8], our algorithm belongs to the family of truncated Newton methods and exploits an efficient matrix-vector product to avoid explicitely storing the natural g…
Proposes baselines for joint NAS and HPO optimization.
A new method uses machine learning to optimize user pairing and association in multicell NOMA networks.
We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments. These image-caption pairs arise frequently in high-value applications where structured training data is e…
Proposes novel losses for fine-grained categorical domain adaptation.
New framework improves LLM performance by avoiding forgetting during sequential training stages.
JoLT uses LLMs to make probabilistic predictions on tabular data.
Efficiently combines autoregressive and set-based models for joint distributions.
We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. A major approach to achieve this objective is to train a model that integrates all the information of different modalities into a joint representation and then t…
We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discriminative architectures ma…
This paper proposes the divergence triangle as a framework for joint training of generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly integrates variational learning, adversarial learning, wake-sleep algorithm, an…
APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.