Research
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

93186278371 · Jun 202019922001200920172026
48 results for Bayesian Last Layer

Bayesian neural network models improve uncertainty quantification in multivariate regression.

problem Uncertainty quantification in multivariate regression models with heteroscedastic noise.
method Proposes Bayesian Last Layer neural network models and EM algorithms for parameter learning.
result Capable of disentangling aleatoric and epistemic uncertainty.

Bayesian optimization improved with variational last layer training.

problem Bayesian optimization performance on complex input correlations.
method Connecting variational Bayesian last layer training to exact conditioning in Gaussian processes, developing an efficient online training algorithm.
result VBLL networks significantly outperform GPs and match well-tuned GPs on benchmark tasks.

Bayesian approach learns invariances from data alone, but last layer approximation is not always sufficient.

problem Learning invariances in neural networks using only training data.
method Bayesian marginal likelihood for last layer, custom optimisation routine, new lower bound.
result Partial success on standard benchmarks and medical imaging dataset, failure on CIFAR10.

Study clarifies Bayesian generalization error in CBM for 3-layered linear neural networks.

problem Understanding the generalization error in concept bottleneck models.
method Mathematical analysis of Bayesian generalization error and free energy in CBM for 3-layered linear neural networks.
result CBM significantly alters the parameter region and Bayesian generalization error compared to standard models.

Last-layer approximation improves UQ performance without sacrificing computational efficiency.

problem Epistemic uncertainty quantification for deep neural networks.
method Comparison of full-network and last-layer linearization using theoretical and empirical approaches.
result Last-layer approximation yields comparable UQ performance with improved computational efficiency.

New method calibrates LLMs for safety-critical tasks with scalable Bayesian inference.

problem Overconfidence in LLMs after fine-tuning for specific tasks.
method Orthogonalized Low-Rank Adapters (PoLAR) with variational Bayesian inference.
result Scalable and well-calibrated uncertainty estimation for LLMs.

Develops multi-modal neural network models for improved prediction and uncertainty quantification.

problem Improving prediction accuracy and uncertainty quantification for multi-modal data.
method Multi-modal Bayesian neural network models with conjugate last-layer estimation using SVI.
result Improved prediction accuracy and uncertainty quantification compared to uni-modal models.

CLAPS improves conformal regression by adaptively scaling interval widths based on last-layer Laplace uncertainty.

problem Lack of adaptive interval width scaling in conformal regression for heterogeneous inputs.
method CLAPS uses heteroscedastic last-layer Laplace uncertainty to adaptively scale interval widths, combining aleatoric and epistemic uncertainties.
result CLAPS provides competitive interval efficiency with nominal-level coverage, reducing to aleatoric scaling as epistemic uncertainty decreases.

Study examines dependence properties of Bayesian neural network units in finite-width networks.

problem Understanding dependence properties of hidden units in practical finite-width Bayesian neural networks.
method Theoretical analysis and empirical evaluation of depth and width impacts.
result Hidden units in finite-width Bayesian neural networks are dependent, contrary to the infinite-width limit assumption.

Last layer retraining improves robustness to spurious correlations without high computational costs.

problem Neural networks can rely on spurious features like backgrounds for predictions.
method Simple last layer retraining on large models.
result Last layer retraining matches or outperforms state-of-the-art approaches on spurious correlation benchmarks.

Optimizes neural networks' last layer with closed-form solutions.

problem Optimizing neural networks' last layer with stochastic gradient descent.
method Adapting closed-form last layer optimization for stochastic gradient descent, alternating between backbone and last layer updates.
result The method converges to optimal solutions and outperforms standard SGD and Adam in regression tasks.

Establishes connection between MTDNN and multitask GP, revealing weight correlation as key to task sharing.

problem Limited theoretical understanding of information sharing in MTDNN.
method Derives multitask GP kernels for MTDNN and MTBNN, showing shared hyper-parameters and last layer weights.
result Information sharing in MTDNN is due to weight correlation, not intermediate layer weights.

We study reinforcement learning (RL) in high dimensional episodic Markov decision processes (MDP). We consider value-based RL when the optimal Q-value is a linear function of d-dimensional state-action feature representation. For instance, in deep-Q networks (DQN), the Q-value is a linear function of the feature repres…

2018-02-13abs ↗pdf ↗

PCBM improves neural network generalization by partially observing concepts.

problem Decreased generalization performance due to observing all concepts in CBM.
method Developed a theoretical analysis of PCBM's Bayesian generalization error.
result PCBM's generalization error is lower than CBM's due to partial concept observation.

Study on hidden units in finite Bayesian neural networks and their tail properties.

problem Understanding the behavior of hidden units in finite Bayesian neural networks.
method Introduced a generalized Weibull-tail property to describe hidden units tails.
result Unit priors become heavier-tailed going deeper, providing insights into finite Bayesian neural networks.

Bayesian linear regression on neural network representations handles both homoscedastic and heteroscedastic noise.

problem Uncertainty in neural network predictions, especially with heteroscedastic noise.
method Proposes a novel Bayesian linear regression approach to model heteroscedastic noise in neural network representations.
result The method outperforms standard ensembling and other methods in model-based reinforcement learning.

Bayesian neural networks approximate Student-t processes in the infinite-width limit.

problem Modeling uncertainty in neural networks with greater flexibility.
method Extending asymptotic properties of Gaussian processes to Student-t processes in the infinite-width limit of BNNs.
result Posterior BNNs converge to Student-t processes in the infinite-width limit.

This research shows loss weighting remains effective in last layer retraining despite model overparameterization.

problem Overcoming biases in machine learning models at scale.
method Theoretical and practical exploration of last layer retraining in an overparameterized setting.
result Loss weighting is still effective in last layer retraining, but weights must account for model overparameterization.

Posterior refinement improves sample efficiency in Bayesian neural networks.

problem Bayesian neural networks suffer from poor predictive performance due to inaccurate posterior approximations.
method Propose refining Gaussian approximate posteriors with normalizing flows to improve predictive distributions.
result Posterior refinement yields competitive predictive performance with minimal computational overhead.

RegVar quantifies uncertainty in deep learning networks by measuring sensitivity to regularization.

problem Uncertainty quantification in deep learning networks, especially for large networks.
method RegVar method based on variation due to regularization, implemented during fine-tuning phase.
result RegVar provides rigorous uncertainty estimates that recover Bayesian deep learning approximations.

Wide neural networks' last hidden layers split into groups of redundant neurons.

problem Understanding why wide neural networks generalize well despite overfitting.
method Analyzed the last hidden layer representations of various convolutional neural networks.
result Wide hidden layers split into groups of redundant neurons, which help generalize.

Deep neural networks converge to Gaussian mixtures as layer width increases.

problem Understanding the distribution of outputs from deep neural networks.
method Proof and experiments with a simple model showing the convergence of neural network outputs to Gaussian mixtures.
result Neural networks converge to Gaussian mixtures as the width of the last hidden layer increases.

We analyze neural collapse in neural networks, showing that features collapse to vertices of a Simplex ETF.

problem Understanding and optimizing the features learned in the last layer of neural networks during training.
method Simplified unconstrained feature model, studying the global optimization landscape of cross-entropy loss with weight decay.
result The global minimizers of the loss are Simplex ETFs, and other critical points are strict saddles with negative curvature.

One of the main challenges of deep learning methods is the choice of an appropriate training strategy. In particular, additional steps, such as unsupervised pre-training, have been shown to greatly improve the performances of deep structures. In this article, we propose an extra training step, called post-training, whi…

2016-11-14abs ↗pdf ↗

Deep reinforcement learning (DRL) methods such as the Deep Q-Network (DQN) have achieved state-of-the-art results in a variety of challenging, high-dimensional domains. This success is mainly attributed to the power of deep neural networks to learn rich domain representations for approximating the value function or pol…

2017-05-21abs ↗pdf ↗

DS-UI improves DNN uncertainty inference by combining a DNN classifier with MoGMM.

problem Improving uncertainty inference in DNN-based image recognition.
method Combines DNN classifier with MoGMM for probabilistic interpretation of features.
result DS-UI outperforms state-of-the-art UI methods in misclassification detection.

RAD improves robustness to domain annotation noise without explicit domain annotations.

problem Robustness to domain annotation noise in training data.
method Regularized Annotation of Domains (RAD) for last layer retraining.
result RAD outperforms state-of-the-art methods even with 5% noise in training data.

We describe Bayesian Layers, a module designed for fast experimentation with neural network uncertainty. It extends neural network libraries with drop-in replacements for common layers. This enables composition via a unified abstraction over deterministic and stochastic functions and allows for scalability via the unde…

2018-12-10abs ↗pdf ↗

Hybrid Bayesian neural networks use function uncertainty for probabilistic inference.

problem Uncertainty in neural network weights is hard to specify and interpret.
method Integrates probabilistic layers with standard deterministic layers for function uncertainty.
result Improves probabilistic inference by encoding function uncertainty.

Bayesian neural networks improve cosmic parameter estimation from modified gravity simulations.

problem Estimating cosmological parameters from large-scale structure data with modified gravity.
method Implement Bayesian neural networks (BNNs) with two cases: single BLL and FullB, trained on dark matter only particle mesh NN-body simulations.
result BNNs yield well-calibrated uncertainty estimates and accurately predict cosmological parameters for ΩmΩ_m and σ8σ_8.

Global inducing points improve Bayesian neural network performance.

problem Improving Bayesian neural network performance.
method Adapting correlated approximate posterior to all layers in a Bayesian neural network and deep Gaussian processes using learned global inducing points.
result State-of-the-art performance on CIFAR-10 (86.7%) without data augmentation or tempering.

Unified Bayesian-AI framework improves epidemiological risk prediction and uncertainty quantification.

problem Lack of calibrated uncertainty in machine learning models for epidemiology.
method Combines Bayesian prediction with Bayesian hyperparameter optimization using logistic regression and Gaussian-process Bayesian optimization.
result Unified Bayesian-AI framework provides reliable coverage and improved calibration, enhancing epidemiological decision making.

New algorithms split deep learning tasks into representation and uncertainty estimation.

problem Challenges in uncertainty quantification for deep learning models.
method Proposes a two-stage approach: representation learning and uncertainty estimation.
result Simple methods outperform complex uncertainty layers in selective classification and out-of-distribution detection.

The monotonic linear interpolation in deep networks often leads to plateaus, revealing biases in optimization.

problem Plateaus in the optimization landscape of deep networks during monotonic linear interpolation.
method Investigated monotonic linear interpolation on deep neural networks, focusing on biases in weights and biases.
result Interpolating weights and biases differently can lead to significant differences in loss and accuracy, revealing biases in optimization.