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.
A new probabilistic polygonal curve representation using Gaussian Mixture Models.
ProSMIN improves representation quality through probabilistic self-supervised learning.
New method improves self-supervised representation learning using probabilistic modeling and Monte Carlo integration.
We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams. This representation al…
Probabilistic models learned as density estimators can be exploited in representation learning beside being toolboxes used to answer inference queries only. However, how to extract useful representations highly depends on the particular model involved. We argue that tractable inference, i.e. inference that can be compu…
The paper extends calibration to sets of probabilistic classifiers, finding many ensembles are poorly calibrated.
Simple method disentangles content and style from pre-trained vision models.
In this work, we introduce a novel probabilistic representation of deep learning, which provides an explicit explanation for the Deep Neural Networks (DNNs) in three aspects: (i) neurons define the energy of a Gibbs distribution; (ii) the hidden layers of DNNs formulate Gibbs distributions; and (iii) the whole architec…
This paper improves DNN generalization by accurately estimating mutual information.
ProbETA models travel time correlations between trips for better navigation.
In this paper we investigate the virtual string links via a probabilistic interpretation. This representation can be used to distinguish some virtual string links from classical string links. In order to study the algebraic structure behind this probabilistic interpretation we introduce the notion of virtual flat biqua…
Probabilistic representations, such as Bayesian and Markov networks, are fundamental to much of statistical machine learning. Thus, learning probabilistic representations directly from data is a deep challenge, the main computational bottleneck being inference that is intractable. Tractable learning is a powerful new p…
TRUST improves structure learning with tractable uncertainty.
NP-HMC extends HMC for nonparametric models in probabilistic programming.
KalMamba improves RL efficiency with probabilistic SSMs.
This paper introduces a probabilistic framework for k-shot image classification. The goal is to generalise from an initial large-scale classification task to a separate task comprising new classes and small numbers of examples. The new approach not only leverages the feature-based representation learned by a neural net…
Proposes a deep probabilistic multi-view model for multi-view learning.
The paper proves probabilistic alignment between unseen modalities using contrastive learning.
Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory. Exploiting this we have …
Paper improves Tm prediction of protein fragments using sparsity and probabilistic models.
We propose Edward, a Turing-complete probabilistic programming language. Edward defines two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as t…
VIR model improves regression accuracy and uncertainty estimation for imbalanced data.
Paper introduces PRMs to learn non-Markovian stochastic rewards for reinforcement learning.
Paper develops a dual formulation for PCA in Hilbert spaces.
A central tenet of probabilistic programming is that a model is specified exactly once in a canonical representation which is usable by inference algorithms. We describe JointDistributions, a family of declarative representations of directed graphical models in TensorFlow Probability.
Unified framework for differentiable graph partitioning with probabilistic cuts.
This paper improves probabilistic latent models on hyperbolic spaces.
In this paper, we propose a probabilistic parsing model, which defines a proper conditional probability distribution over non-projective dependency trees for a given sentence, using neural representations as inputs. The neural network architecture is based on bi-directional LSTM-CNNs which benefits from both word- and …
The paper shows how to answer future and past questions from high-dimensional time series data.
CAMul forecasts with calibrated and accurate multi-view time-series data.
We would like to learn a representation of the data which decomposes an observation into factors of variation which we can independently control. Specifically, we want to use minimal supervision to learn a latent representation that reflects the semantics behind a specific grouping of the data, where within a group the…
Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We discuss probabilistic and generative deep learning, which generative concept re…
SPPL simplifies probabilistic programming for exact inference.
Paper proposes a probabilistic alignment method for domain adaptation.
Unified framework for learning flexible probabilistic programs using DPP and PAC-Bayes bounds.
New method enforces encoder sparsity in HPF for more interpretable feature selection.
We present sparse topical coding (STC), a non-probabilistic formulation of topic models for discovering latent representations of large collections of data. Unlike probabilistic topic models, STC relaxes the normalization constraint of admixture proportions and the constraint of defining a normalized likelihood functio…
New method learns interaction-aware orderbook representation for better intraday electricity price forecasting.
Probabilistic representations, such as Bayesian and Markov networks, are fundamental to much of statistical machine learning. Thus, learning probabilistic representations directly from data is a deep challenge, the main computational bottleneck being inference that is intractable. Tractable learning is a powerful new p…
Bayesian scores improve structure learning in probabilistic circuits.
Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has been devoted to encoding invariance under symmetry transformations into neural n…
ROOTS learns to represent and render 3D scenes with object-centric models.
Many data-driven approaches exist to extract neural representations of functional magnetic resonance imaging (fMRI) data, but most of them lack a proper probabilistic formulation. We propose a group level scalable probabilistic sparse factor analysis (psFA) allowing spatially sparse maps, component pruning using automa…
Sum-Product Networks (SPNs) are recently introduced deep tractable probabilistic models by which several kinds of inference queries can be answered exactly and in a tractable time. Up to now, they have been largely used as black box density estimators, assessed only by comparing their likelihood scores only. In this pa…
Probabilistic representations of movement primitives open important new possibilities for machine learning in robotics. These representations are able to capture the variability of the demonstrations from a teacher as a probability distribution over trajectories, providing a sensible region of exploration and the abili…
Method transfers feature representation from large to small models using perception coherence.
VJE learns latent representations without contrastive learning, providing probabilistic semantics.
A new probabilistic BTD method for tensor data.