We consider reinforcement learning in parameterized Markov Decision Processes (MDPs), where the parameterization may induce correlation across transition probabilities or rewards. Consequently, observing a particular state transition might yield useful information about other, unobserved, parts of the MDP. We present a…
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.
169,181 papers · 148 categories
Trend · papers per month
48 results for “parameterized priors”
Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterizationcs.LG
Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.
problem Robust recovery of low-rank matrices from grossly corrupted measurements.
method Gradient descent with discrepant learning rates for double over-parameterized models.
result Gradient descent with discrepant learning rates provably recovers the underlying matrix without prior knowledge on rank or sparsity.
New method uses quotient predictor space for better PAC-Bayes bounds, reducing KL divergence and improving model performance.
problem Overparameterized models with continuous symmetries can lead to biased predictions.
method Perform PAC-Bayesian analysis on quotient predictor space, constructing a canonical prior that reflects model's implicit bias.
result The new prior reduces KL divergence and improves model performance in experiments.
A new method converts neural networks to function space for scalable sequential learning.
problem Challenges in gradient-based deep learning for sequential data.
method Dual parameterization of neural networks from weight to function space.
result Efficient scaling, knowledge retention, and new data incorporation.
Rényi Neural Processes replace KL divergence with Rényi divergence to improve NP performance.
problem Parameterization coupling in Neural Processes leads to prior misspecification.
method Propose Rényi Neural Processes (RNP) by replacing KL divergence with Rényi divergence.
result Significant performance improvements in real-world problems, including better log-likelihoods.
Least squares regression shows unexpected double descent in under-parameterized models.
problem Understanding the generalization of under-parameterized models in regression.
method Analyzing the spectrum and eigenvectors of the sample covariance matrix.
result Least squares regression can exhibit a peak in generalization in the under-parameterized regime, contrary to previous explanations.
We introduce new definitions of universal and superuniversal computable codes, which are based on a code's ability to approximate Kolmogorov complexity within the prescribed margin for all individual sequences from a given set. Such sets of sequences may be singled out almost surely with respect to certain probability …
New algorithm scales model-based policy search for robotics to high-dimensional systems.
problem Inefficient scaling of model-based policy search algorithms in high-dimensional state/action spaces.
method Introduces parameterized black-box priors to scale up model learning and improve robustness to prior inaccuracies.
result Significantly more data-efficient than previous algorithms, learning gaits in 16-30 seconds.
The paper proposes methods for volumetric parameterization of 3D solid manifolds.
problem Complex structure of solid manifolds makes conventional approaches ineffective.
method Incorporates models to preserve geometric structure, achieve density equalization, and balance distortions.
result Various 3D manifold parameterizations with different properties can be achieved.
Develops a method for conformal parameterization of point clouds without fixed boundaries.
problem Desirable distortion in fixed-boundary parameterizations of point clouds.
method Free-boundary conformal parameterization method involving approximation of point cloud Laplacian and boundary treatment.
result High-quality point cloud meshing achieved through the proposed method.
Study bounds graph neural networks' over-parameterized error.
problem Understanding graph neural networks' performance in over-parameterized regimes.
method Developed mean-field regime bounds for graph convolutional and message passing neural networks.
result Established upper bounds with a convergence rate of for generalization error.
Scalable multi-task regression via sparse Gaussian process priors.
problem Efficiently modeling and predicting multiple related tasks.
method Direct Cholesky factorization for sparse parameterization of Gaussian process priors.
result Sparse parameterization improves scalability and accuracy in multi-task regression.
Predictive Complexity Priorsstat.ML
Proposes a new prior for complex models to improve prediction accuracy.
problem Difficulty in specifying priors for complex models like neural networks.
method Predictive complexity priors defined by comparing model predictions to a reference model, transferred to parameters via change of variables.
result Improves model predictions by reducing unintuitive effects of traditional priors.
Improved analysis shows milder over-parameterization for deep neural networks.
problem Ensuring global convergence of over-parameterized deep neural networks.
method Improved analysis of gradient descent for training deep neural networks.
result Milder over-parameterization condition than previous work.
Local PCA detects intrinsic parameterization of complex thermo-chemical state-spaces.
problem Detecting intrinsic parameterization of complex thermo-chemical state-spaces.
method Local PCA applied to local clusters of data.
result Local PCA finds meaningful parameterization linked to local stoichiometry, reaction progress, and soot formation processes.
Unified framework for nonconvex matrix completion with linearly parameterized factors.
problem Matrix completion with improved accuracy using linearly parameterized factors.
method Unified nonconvex optimization framework with Correlated Parametric Factorization condition.
result Uniform upper bounds for low-rank estimation at any local minimum.
New methods solve tensor-on-tensor regression with unknown rank, revealing benefits of over-parameterization.
problem Connecting tensor responses to tensor covariates with unknown intrinsic rank.
method Riemannian gradient descent and Riemannian Gauss-Newton methods for tensor-on-tensor regression.
result Riemannian optimization methods converge linearly and quadratically to a statistically optimal estimate in rank over-parameterized settings.
The paper analyzes how over-parameterization affects GD convergence in matrix sensing problems.
problem Matrix sensing problem with over-parameterized gradient descent.
method Analyzes symmetric and asymmetric parameterizations, provides lower bounds and convergence rates.
result Over-parameterization slows down GD convergence, but asymmetric parameterization can speed up convergence.
Efficiently reconstructs jump-diffusion processes from data using neural networks.
problem Reconstructing jump-diffusion processes from data.
method Temporally decoupled squared Wasserstein distance method using parameterized neural networks.
result Enhanced reconstruction of jump-diffusion processes from data.
Introduces a neural network-based method for efficient state and parameter estimation in complex systems.
problem Efficiently estimating state paths and parameters from noisy measurements in high-dimensional nonlinear systems.
method Bayesian Information Field Theory with neural network parameterization and optimization algorithms.
result Proposes a method to simplify and enrich state path parameterizations using neural networks, improving inference accuracy.
The paper analyzes optimal implicit bias in linear regression for over-parameterized models.
problem Finding the best generalization performance in over-parameterized linear regression.
method Asymptotic analysis of generalization performance for convex functions/potentials.
result Optimal implicit bias that achieves the best generalization error under certain conditions.
Student- processes have recently been proposed as an appealing alternative non-parameteric function prior. They feature enhanced flexibility and predictive variance. In this work the use of Student- processes are explored for multi-objective Bayesian optimization. In particular, an analytical expression for the h…
Introduces Causal Energy Minimization to understand Transformer layers.
problem Empirical parameterization of Transformer blocks remains largely unexplored.
method Causal Energy Minimization framework that recasts Transformer layers as optimization steps on conditional energy functions.
result Identifies design space for Transformer layers including weight sharing and energy-based interpretations.
DMSTF models spatio-temporal data with deep Markov priors.
problem Analyzing nonlinear multimodal spatio-temporal dynamics.
method Deep Markov spatio-temporal factorization with stochastic variational inference.
result DMSTF outperforms other methods in predictive performance and clustering.
This paper introduces a new neural ODE model for continuous-time sequence generation.
problem Representing and predicting continuous-time sequences with high accuracy.
method A neural emission model and neural ODE define the latent state evolution, with an Energy-based model for prior distribution.
result The model outperforms existing methods in various tasks, including long-horizon predictions.
Randomly trained neural networks can generalize well if there's a simpler underlying teacher model.
problem Why randomly trained neural networks generalize well despite interpolating training data.
method Examined a random neural network that interpolates training data and showed it generalizes well if there's a simpler underlying teacher model.
result Randomly trained neural networks can generalize well if there's a simpler underlying teacher model.
New method samples Jeffreys prior for objective Bayesian inference.
problem Sampling from Jeffreys prior is challenging.
method Metropolis-Adjusted Langevin Algorithm
result Samples can be directly used in Bayesian methods.
In this paper we present decomposable priors, a family of priors over structure and parameters of tree belief nets for which Bayesian learning with complete observations is tractable, in the sense that the posterior is also decomposable and can be completely determined analytically in polynomial time. This follows from…
Optimality of TS with noninformative priors proven for Pareto model.
problem Optimality of Thompson Sampling with noninformative priors for Pareto bandits.
method Proved optimality of TS with certain probability matching priors, showed suboptimality with others, and found effectiveness of truncation procedures.
result TS with certain probability matching priors achieves optimal regret bound for Pareto model.
Develops VAEs for learning complex physical systems from data.
problem Learning low-dimensional representations of nonlinear physical systems.
method Variational Autoencoders with manifold latent spaces.
result Effective in learning nonlinear Burgers equation and constrained mechanical systems.
Unified approach to VAEs using flexible priors and inverse AFs.
problem Improving VAEs for better sample generation and inference.
method Layerwise density estimation, inverse autoregressive flows (inverse AF).
result Inverse AF can approximate any posterior, improving VAEs.
Deeper quantum circuits can improve performance on unseen data, contrary to traditional views.
problem Understanding scaling behavior of parameterized quantum circuits and their generalization.
method Gradient-based PQCs, add-one-in perturbation techniques, spectral properties of random matrices.
result Gradient-based PQCs can exhibit improved performance on unseen data as model size increases, displaying double descent behavior.
New method reduces over-pessimism in Bayesian control under parameter uncertainty.
problem Over-pessimism in Bayesian control due to misspecified priors.
method Distributionally robust Bayesian control (DRBC) with strong duality and optimization.
result Validated algorithm on synthetic and real data, reducing over-pessimism.
A quantum circuit designed for efficient statistical model preparation and training.
problem Challenges in preparing and learning statistical models on quantum processors.
method Utilizes the maximum entropy principle to design a statistics-informed parameterized quantum circuit (SI-PQC).
result Improves trainability and interpretability for learning quantum states and classical model parameters.
New method reduces DSI complexity using RAE and LSTM for better posterior predictions.
problem Reducing complexity in data-space inversion for subsurface flow simulations.
method Recurrent Autoencoder (RAE) for dimension reduction and LSTM for flow-rate time series representation.
result RAE-based parameterization outperforms existing DSI treatments in statistical agreement with reference results.
Linear models can overfit without harming OOD generalization under certain conditions.
problem Understanding how overparameterized linear models generalize to out-of-distribution data.
method Analyzing overparameterized linear models under covariate shift, providing guarantees for OOD generalization.
result Benign overfitting occurs in standard ridge regression under OOD conditions, with specific structural conditions on target covariance.
Bayesian inference using particle flow and neural operators.
problem Efficiently updating beliefs with new data.
method ODE-based neural operator for particle flow, meta-learning for generalization.
result Generalization across different priors, observations, and sequential inference.
We investigate a local reparameterizaton technique for greatly reducing the variance of stochastic gradients for variational Bayesian inference (SGVB) of a posterior over model parameters, while retaining parallelizability. This local reparameterization translates uncertainty about global parameters into local noise th…
New method uses generative priors for compressive sensing with sparse solutions.
problem Fundamental linear inverse problem in compressive sensing.
method Sparse Bayesian learning with conditional Gaussianity.
result Ability to learn from few compressed and noisy samples without optimization.
The paper validates a method for recovering over-parameterized matrices and images from noisy measurements.
problem Recovering a low-rank matrix from noisy measurements when the rank is unknown.
method Using gradient descent with small random initialization on a nonconvex objective function built from a rank-overspecified factored representation of the matrix variable.
result Gradient descent iterations converge to the ground-truth matrix under certain conditions and can be stopped efficiently to detect a nearly optimal estimator.
Generative models learn better with data-adaptive noise.
problem Learning heavy-tailed distributions in flow-based models.
method Data-adaptive latent noise using 1D quantile functions optimized via Wasserstein distance.
result Flexibility and effectiveness in learning heavy-tailed and compactly supported distributions.
Wide hypernetworks don't guarantee convergence under gradient descent.
problem Theoretical guarantees for wide hypernetworks in over-parameterized settings.
method Analyzing infinitely wide hypernetworks and their convergence properties.
result Infinitely wide hypernetworks do not guarantee convergence to a global minimum under gradient descent.
New neural network model reduces complexity of geological media sampling.
problem Efficient and high-fidelity sampling of complex binary geological media.
method Variational autoencoder-based deep neural network for low-dimensional base model parameterization.
result Our DR approach outperforms PCA, OPCA, and DCT in probabilistic inversion.
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernelsstat.ML
New insights into model robustness for random features and NTK models.
problem Understanding and distinguishing robustness in machine learning models.
method Analyzing empirical risk minimization in random features and NTK models.
result Random features models are not robust under any degree of over-parameterization, even when satisfying the universal law of robustness.
Advances smooth over-parameterization for solving non-smooth optimization problems.
problem Non-smooth optimization with structural constraints in imaging and machine learning.
method Smooth over-parameterization of non-smooth problems, using gradient descent and mirror descent.
result Gradient descent on the reformulated smooth problem converges efficiently without parameter tuning.
Bayesian model predicts fashion size recommendations and returns.
problem Predicting optimal fashion sizes and handling returns efficiently.
method Hierarchical Bayesian model for size and return events.
result Model incorporates domain expertise and article characteristics.
Study motion planning for points avoiding obstacles in a plane.
problem Avoiding collisions for multiple points in a plane with unknown obstacles.
method Algebraic and topological tools for motion planning.
result New topological complexity for planar motion planning.
Improved neural network training by coupled initialization reduces neuron count.
problem Training neural networks efficiently with fewer neurons.
method Coupled initialization of weights into pairs of identical Gaussian vectors.
result Significantly reduced number of neurons required for network convergence.