Single-pass method estimates neural network uncertainty.
problem Uncertainty estimation in deep learning requires multiple passes.
method Probabilistic reasoning over neural network depths.
result Single forward pass for uncertainty estimation.
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Probabilistic Forward Pass”
PFP-BNNs offer a fast, deterministic approach to Bayesian neural networks.
problem Limited uncertainty handling in traditional neural networks restricts their use in safety-critical settings.
method Probabilistic Forward Pass (PFP) approximates Stochastic Variational Inference (SVI) for efficient BNNs.
result PFP-BNNs achieve up to 4200x speedup over SVI-BNNs while maintaining similar accuracy and uncertainty.
This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing probabilistic interpretations of meta-learning to cover a broad class of methods. 2) We i…
Cascading flows improve variational inference in structured programs.
problem Challenges in variational inference for complex probabilistic programs.
method Integrates normalizing flows and ASVI to create cascading flows, which embed the forward-pass of probabilistic programs.
result Cascading flows outperform normalizing flows and ASVI in structured inference problems.
BLISS detects and separates astronomical sources quickly and accurately.
problem Detecting and separating overlapping astronomical sources in large images.
method Bayesian Light Source Separator (BLISS) using deep generative models and variational inference.
result BLISS can process megapixel images in seconds and produce highly accurate catalogs.
Proposes a method to use generators as EBM foundations without latent inference.
problem Training EBMs from generator outputs without latent variables.
method Formulates a Hat EBM using generator outputs and residual variables.
result Strong performance on various generator tasks.
Improved DDPMs achieve high log-likelihoods and sample quality with fewer passes.
problem Improving log-likelihoods of DDPMs while maintaining high sample quality.
method Modifying DDPMs with learning variances and using precision-recall metrics.
result DDPMs can achieve competitive log-likelihoods with fewer forward passes.
DistPred provides a fast, distribution-free method for regression and forecasting.
problem Deterministic point estimates in regression and prediction tasks.
method Transforming proper scoring rules into a differentiable form and using it as a loss function.
result Achieved state-of-the-art performance and significantly improved computational efficiency.
Graph-EFM models weather uncertainty with graph-based ensembles.
problem Accurately capturing forecast uncertainty in chaotic weather.
method Flexible latent-variable formulation with hierarchical graph construction.
result Graph-EFM ensembles achieve equivalent or lower errors than deterministic models.
SGD converges with perturbed forward-backward passes, explained by geometric amplification.
problem Analyzing convergence of SGD with perturbed forward-backward passes in composite optimization.
method Characterized propagation and amplification of perturbations, derived convergence guarantees for non-convex and PL objectives.
result Perturbations cascade through the computational graph, affecting convergence order under specific conditions.
SHINE uses forward pass quasi-Newton matrices to approximate Jacobian inverses for faster bi-level optimization.
problem Efficiently solving bi-level optimization problems with large Jacobian matrices.
method Proposes using quasi-Newton matrices from the forward pass to approximate the inverse Jacobian matrix.
result Empirically shows SHINE reduces computational cost of the backward pass for various problems.
Factor graphs have recently gained increasing attention as a unified framework for representing and constructing algorithms for signal processing, estimation, and control. One capability that does not seem to be well explored within the factor graph tool kit is the ability to handle deterministic nonlinear transformati…
Paper introduces efficient uncertainty estimation in LLMs without multiple forward passes.
problem Accurate uncertainty quantification in LLMs remains challenging.
method Evidential Knowledge Distillation to create compact student models.
result Efficient uncertainty estimation achieved with single forward pass.
This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration. Selective-Backprop uses the output of a training example's forward pass to decide whether to use that example to compute gradients and update para…
ASVI automates variational inference for complex models.
problem Efficient variational inference for complex probabilistic models.
method Automatic structured variational inference (ASVI) using convex updates.
result ASVI outperforms other methods on a wide range of problems.
DG improves policy gradient efficiency by selectively backpropagating only valuable samples.
problem Expensive backward passes in policy gradient methods reduce efficiency.
method Introduces 'delight' as a forward-pass signal of learning value and a Kondo gate to selectively backpropagate.
result Selective backpropagation reduces backward pass costs without sacrificing learning quality.
SymNet uses neural models to solve RMDPs efficiently.
problem Limited effectiveness of generalized policies in RMDPs.
method SymNet trains shared parameters for an RDDL domain, converts instances to graphs, uses relational neural models for node embeddings, and scores actions based on embeddings.
result SymNet policies outperform random and state-of-the-art deep reactive policies on nine RDDL domains.
Understanding the dynamics of message passing algorithms: a free probability heuristicscond-mat.stat-mech
Analyze message passing algorithms using free probability theory.
problem Dynamics of message passing algorithms for probabilistic models.
method Use freeness assumptions of random matrix theory.
result Recover and analyze properties of message passing algorithms.
SDPA is shown to be an optimal transport problem in deep learning.
problem The mathematical foundation and optimization perspective of SDPA.
method SDPA is shown to be the exact solution to a degenerate, one-sided Entropic Optimal Transport (EOT) problem.
result The SDPA mechanism is a principled mechanism where the forward pass performs optimal inference and the backward pass implements a rational, manifold-aware learning update.
We reduce training time in convolutional networks (CNNs) with a method that, for some of the mini-batches: a) scales down the resolution of input images via downsampling, and b) reduces the forward pass operations via pooling on the convolution filters. Training is performed in an interleaved fashion; some batches unde…
We propose the Limited Multi-Label (LML) projection layer as a new primitive operation for end-to-end learning systems. The LML layer provides a probabilistic way of modeling multi-label predictions limited to having exactly k labels. We derive efficient forward and backward passes for this layer and show how the layer…
Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scalecs.LG
LayerNorm transformers have dead directions that can be read from their parameters alone.
problem Locating dead directions in LayerNorm transformers
method Using the inverse-scale direction of LayerNorm affine parameters
result Predicted dead direction matches measured bottom singular direction
Automates model comparison in probabilistic programming.
problem Manual derivations for model comparison are error-prone and time-consuming.
method Message passing on a Forney-style factor graph with a custom mixture node.
result Automates Bayesian model averaging, selection, and combination.
Predicting human behavior is a difficult and crucial task required for motion planning. It is challenging in large part due to the highly uncertain and multi-modal set of possible outcomes in real-world domains such as autonomous driving. Beyond single MAP trajectory prediction, obtaining an accurate probability distri…
A method makes particle filters differentiable without altering their forward pass.
problem Compatibility issues between particle filters and automatic differentiation.
method Introduces a correction to particle weights using the stop-gradient operator.
result Automatic differentiation produces good estimators for gradients and second-order derivatives.
Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called Deep Learning Approximation to build a faster network in a tiny fraction of the …
Proposes a deep model for Bayesian quantile regression without Gaussian assumptions.
problem Uncertainty quantification from single forward-pass models is computationally expensive and restrictive.
method Deep evidential learning for Bayesian quantile regression.
result Achieves calibrated uncertainties on non-Gaussian distributions.
Bayesian neural networks (BNNs) have developed into useful tools for probabilistic modelling due to recent advances in variational inference enabling large scale BNNs. However, BNNs remain brittle and hard to train, especially: (1) when using deep architectures consisting of many hidden layers and (2) in situations wit…
VFG model embeds flow-based models with hierarchical structures using variational inference.
problem Flow-based models struggle with high-dimensional latent spaces and lack of tractable inference for graphical structures.
method Integrates flow-based functions through variational inference with aggregation nodes for hierarchical information integration.
result VFG models achieve improved ELBO and likelihood values on multiple datasets.
Simple neural net outperforms complex uncertainty methods.
problem Reliable uncertainty estimation from deterministic models.
method A simple baseline using a single softmax neural net with residual connections and spectral normalization.
result Simple neural net outperforms DUQ and SNGP on uncertainty prediction.
We propose a framework for the derivation and evaluation of distributed iterative algorithms for receiver cooperation in interference-limited wireless systems. Our approach views the processing within and collaboration between receivers as the solution to an inference problem in the probabilistic model of the whole sys…
Backpropagation-free RL method trains layers using local signals.
problem Vanishing or exploding gradients in backpropagation-based RL.
method Local pairwise distance matching for layer-wise training without backpropagation.
result Backpropagation-free method achieves competitive performance and stability.
A new model improves uncertainty estimation in deep learning.
problem Deep Kernel Learning (DKL) produces unreliable uncertainty estimates.
method Proposed a bi-Lipschitz constraint to preserve distances in feature space.
result DUE model outperforms previous DKL and other methods in uncertainty quality.
Innovative PGMs match neural networks, revealing precise approximations during forward propagation.
problem Lack of precise semantics and probabilistic interpretation in neural networks.
method Constructing infinite tree-structured PGMs that correspond to neural networks.
result DNNs perform precise approximations of PGM inference during forward propagation.
A new method for efficient probabilistic meta-learning.
problem High-quality predictions with well-calibrated uncertainty estimates require large amounts of data.
method Amortised Inference in Bayesian Neural Networks (APOVI-BNN)
result The APOVI-BNN produces high-quality predictions with well-calibrated uncertainty estimates using significantly less data.
Convolutional neural networks (CNN) have led to many state-of-the-art results spanning through various fields. However, a clear and profound theoretical understanding of the forward pass, the core algorithm of CNN, is still lacking. In parallel, within the wide field of sparse approximation, Convolutional Sparse Coding…
We prove here a general closed-form expansion formula for forward-start options and the forward implied volatility smile in a large class of models, including the Heston stochastic volatility and time-changed exponential Lévy models. This expansion applies to both small and large maturities and is based solely on the p…
We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive property of our model is that both p(features), the density of the features, and p(targets | features), the predictive distribution, can be co…
We propose a new variational inference algorithm for learning in Gaussian Process State-Space Models (GPSSMs). Our algorithm enables learning of unstable and partially observable systems, where previous algorithms fail. Our main algorithmic contribution is a novel approximate posterior that can be calculated efficientl…
Derives VMP for LDA, simplifying inference for topic modeling.
problem Manual derivation of VMP equations for LDA is challenging and time-consuming.
method Detailed derivation of VMP update equations for LDA.
result Enables easier implementation of VMP for LDA models.
Probabilistic Skip Connections for Deterministic Uncertainty Quantification in Deep Neural Networkscs.LG
Proposes PSCs for UQ in deep nets without retraining.
problem Estimating uncertainty in deep nets with a single pass.
method Identifies sensitive, smooth intermediate layer, fits probabilistic model.
result PSCs achieve UQ and OOD detection performance matching existing methods.
MPLP learns neural network weights by treating operations as message-passing agents.
problem Training neural networks using gradient-based methods.
method MPLP abstracts neural network operations as message-passing agents, updating internal states and passing messages.
result MPLP outperforms traditional gradient-based methods on simple feed-forward neural networks.
A general graph-structured neural network architecture operates on graphs through two core components: (1) complex enough message functions; (2) a fixed information aggregation process. In this paper, we present the Policy Message Passing algorithm, which takes a probabilistic perspective and reformulates the whole inf…
We begin by reiterating that common neural network activation functions have simple Bayesian origins. In this spirit, we go on to show that Bayes's theorem also implies a simple recurrence relation; this leads to a Bayesian recurrent unit with a prescribed feedback formulation. We show that introduction of a context in…
Neural Clustering Processesstat.ML
Probabilistic clustering models (or equivalently, mixture models) are basic building blocks in countless statistical models and involve latent random variables over discrete spaces. For these models, posterior inference methods can be inaccurate and/or very slow. In this work we introduce deep network architectures tra…
Physics-informed deep learning for PDEs solves forward and inverse problems efficiently.
problem Solving forward and inverse problems in parametric PDEs efficiently and accurately.
method Physics-informed deep latent variable model (PDDLVM) combining deep neural networks, probabilistic modelling, and variational inference.
result Achieves up to three orders of magnitude speed-up compared to traditional FEM while providing coherent uncertainty estimates.
CPS solves inverse problems using forward passes and constrained particle seeking.
problem Solving inverse problems with limited forward observation information.
method Gradient-free approach that reformulates inverse problem as constrained optimization.
result CPS achieves results comparable to gradient-based methods while outperforming alternatives.
Structural and Convergence Analysis of Discrete-Time Denoising Diffusion Probabilistic Modelsmath.PR
The paper analyzes the probabilistic structure of DDPMs and bounds their sampling error.
problem Understanding and controlling errors in discrete-time DDPMs.
method Structural analysis of score functions, Schrödinger's problem, and FBSDEs.
result Explicit upper bound for total variation distance between sampling and target distributions.