The paper interprets VQ-VAE loss as a form of information bottleneck.
problem Understanding the VQ-VAE loss function.
method Interpreted VQ-VAE loss as variational deterministic information bottleneck (VDIB) and variational information bottleneck (VIB).
result VQ-VAE loss can be derived from VDIB and approximated by VIB.
New approach uses physics principles to improve business analytics.
problem Current business analytics methods fail with new data.
method Divide KPIs into controllable and uncontrollable groups; apply physics principles to controllable ones.
result Improves understanding and optimization of controllable KPI dynamics.
Random walks on hyperbolic spaces follow predictable large deviation principles.
problem Understanding the behavior of random walks on hyperbolic spaces.
method Large deviation principles for displacement and translation distances.
result Translation and displacement distances satisfy large deviation principles with the same rate function.
The paper proves a large deviation principle for Gibbs measures on Polish spaces and applies it to specific cases.
problem Large deviation principles for Gibbs measures on Polish spaces.
method General Laplace principle for non-normalized Gibbs measures, applied to conditional Gibbs measures, Coulomb gases, and Fekete points.
result The Laplace principle is proven and applied to specific cases, providing a deterministic version of Γ Γ Γ -convergence. Paper explores SVGD for Bayesian inference, linking deterministic and stochastic dynamics.
problem Bayesian inference and Markov chain Monte Carlo methods.
method Stein variational gradient descent (SVGD) with deterministic and stochastic dynamics.
result Identifies Stein-Fisher information as the leading order contribution in the long-time and many-particle regime.
Develops a new reinforcement learning framework for complex control problems.
problem Continuous-time extended mean field control with deterministic policies.
method Model-free sensitivity formula, deterministic policy gradient, local value and advantage-rate representations.
result Demonstrates efficiency, stability, and robustness in solving complex control problems.
Probabilistic grammars improve equation discovery from data.
problem Discovering scientific laws from data using equations.
method Proposed probabilistic context-free grammars to encode soft constraints and a Monte-Carlo algorithm.
result Probabilistic grammars lead to more efficient equation discovery.
VCL adds uncertainty to contrastive learning models.
problem Lack of uncertainty quantification in contrastive learning methods.
method VCL uses a decoder-free framework that maximizes ELBO with InfoNCE loss and KL divergence.
result VCL provides meaningful uncertainty estimates and matches deterministic baselines in accuracy.
Electrostatics method samples complex distributions deterministically.
problem Sampling and inference of complex, high-dimensional distributions.
method Electrostatics-based particle system with Newton mechanics principles.
result Method achieves comparable performance to other methods in benchmark tasks.
SPECTRA improves probabilistic energy forecasting by separating trends and uncertainties.
problem Interacting uncertainties from renewable intermittency, demand flexibility, market volatility, and weather impact probabilistic forecasts.
method Adaptive state-space exogenous context and temporal-frequency resolution architecture.
result Achieved best CRPS in 14 out of 18 settings, reducing CRPS by 5.74% and upper-tail quantile risk by 7.27%.
KalMamba improves RL efficiency with probabilistic SSMs.
problem Efficiency in learning and inference for probabilistic SSMs in RL.
method Combines Mamba's scalability with Kalman filtering for efficient probabilistic SSMs.
result KalMamba outperforms state-of-the-art SSMs in RL, especially on longer sequences.
Bayesian method for estimating quantile sets efficiently.
problem Estimating quantile sets of expensive-to-evaluate functions.
method Bayesian active learning with Gaussian process modeling and Expected Estimator Modification (EEM).
result Efficient estimation of small quantile sets.
New framework for evaluating ad auctions using stochastic modeling.
problem Challenges in evaluating deterministic ad auctions.
method Repurposed bid landscape model to approximate propensity scores, enabling robust OPE estimators.
result Remarkable alignment with online A/B test results, achieving 92% MDA in CTR prediction.
Non-autoregressive model speeds up sequence generation tasks.
problem Efficiency in sequence generation tasks.
method Iterative refinement based on latent variable models and denoising autoencoders.
result Significant speedup in decoding with comparable quality.
Bayesian scores improve structure learning in probabilistic circuits.
problem Improper structure learning in probabilistic circuits based on heuristics.
method Developed Bayesian structure scores for deterministic PCs, using them in a greedy cutset algorithm.
result Effective protection against overfitting and fast, almost hyper-parameter-free structure learner.
Bayesian method for estimating inputs leading to specific probability outputs.
problem Estimating inputs for specific probability outputs of uncertain functions.
method Bayesian strategy using Gaussian process modeling and SUR principle.
result Surpassed performance of existing methods through numerical experiments.
New method calculates Shapley values for uncertain functions.
problem Uncertain value functions in explainable machine learning.
method Definition of Shapley values using probability theory.
result Shapley values can be applied to uncertain functions.
In a market of deterministic cash flows, given as an additive, symmetric relation of exchangeability on the finite signed Borel measures on the non-negative real time axis, it is shown that the only arbitrage-free price functional that fulfills some additional mild requirements is the integral of the unit zero-coupon b…
A research frontier has emerged in scientific computation, wherein numerical error is regarded as a source of epistemic uncertainty that can be modelled. This raises several statistical challenges, including the design of statistical methods that enable the coherent propagation of probabilities through a (possibly dete…
SNGP improves DNNs' uncertainty estimation with minimal changes.
problem Uncertainty estimation in deep learning models for real-time applications.
method Formalizing uncertainty as a minimax problem, SNGP adds weight normalization and replaces the output layer with a Gaussian process.
result SNGP outperforms other single-model approaches in uncertainty estimation across vision and language tasks.
Study Epstein-Zin preferences in mean field portfolio games, proving unique equilibria.
problem Analyzing portfolio games with Epstein-Zin preferences under non-Markovian conditions.
method Proves a one-to-one correspondence between Nash equilibria and BSDE solutions, using local stochastic maximum principle tailored to Epstein-Zin utility.
result Establishes uniqueness of equilibria in mean field portfolio games under Epstein-Zin preferences.
DeepCSO model forecasts CSO events from multiple sewer structures in near real-time.
problem Forecasting Combined Sewer Overflow (CSO) events at a citywide level.
method Multi-task deep learning model combining data-driven and deterministic methods.
result Deep learning model outperforms traditional methods in CSO event forecasting.
Entropic herding generates smooth distributions for probabilistic modeling.
problem Generating smooth distributions for probabilistic modeling.
method Derives entropic herding as optimization of maximum entropy principle.
result Entropic herding generates smoother distributions than original herding.
The paper solves portfolio selection for complex preferences in continuous time.
problem Dynamic portfolio selection for nonlinear preferences with time inconsistency.
method Stochastic maximum principle and verification theorems for equilibrium strategies.
result Equilibrium strategies derived in closed form for CRRA and CARA preferences.
Efficient methods accelerate diffusion model sampling.
problem Slow sample generation in diffusion models.
method Conjugate Integrators and Splitting Integrators.
result Hybrid method achieves best FID scores.
New method makes variational inference robust for Bayesian neural networks.
problem Fragility of variational Bayes in neural networks.
method Deterministic approximation of moments and hierarchical prior selection.
result Good predictive performance in heteroscedastic regression.
Paper develops a new method for calculating the probability density of a fractional SABR model.
problem Lack of probability density calculations for lognormal fractional SABR model.
method Bridge representation in Fourier space, small time asymptotic expansion, large deviations principle derivation.
result Developed a method to calculate the probability density of fractional SABR model.
This article connects reinforcement learning to probabilistic inference.
problem Intelligent decision making under uncertainty.
method Generalization of reinforcement learning to probabilistic inference.
result Maximum entropy reinforcement learning is equivalent to probabilistic inference.
This note fills the gap in market-consistent valuation of lifelong health insurance products.
problem Market-consistent valuation of lifelong health insurance products is not well-addressed.
method Constructs a valuation portfolio to separate Best Estimate into policy data and financial instrument prices.
result The Best Estimate valuation is not uniquely determined by prevailing term structures and requires a stochastic model.
Paper presents a new way to analyze machine learning generalization without probabilistic assumptions.
problem Traditional generalization analysis assumes i.i.d. data, which is often unverifiable.
method Uses sensitivity analysis of optimization problems to derive deterministic generalization bounds.
result Obtains generalization bounds that relate in-sample and out-of-sample evaluations through an error term quantifying data similarity.
Paper proposes a new method for exact recovery in robust tensor principal component analysis.
problem Exact recovery of low-rank and sparse components in tensors.
method Proposes a new method based on tensor-tensor product and t-SVD to solve a convex optimization problem.
result Exact recovery achieved in a deterministic fashion without randomness assumptions.
Geometric framework links clustering accuracy to structural recovery.
problem Understanding the trade-off between robustness and sensitivity in clustering.
method Develops a clustering condition number to compare within-cluster scale to the minimum loss increase required to move a point across a cluster boundary.
result Sharp phase transitions for exact recovery under different objectives, providing geometric principle for interpreting low objective values.
Develops a new approach to optimal control of stochastic systems.
problem Optimal control of stochastic nonlinear dynamical systems is challenging.
method Formulates optimal control as input estimation, using probabilistic inference and Expectation Maximization.
result Extracts time-varying linear Gaussian feedback controllers from the joint state-action distribution.
Developed mlf-core for deterministic machine learning.
problem Ensuring machine learning models are deterministic for verification.
method Formulated requirements, developed mlf-core ecosystem, tested various models.
result Demonstrated deterministic models in biomedical fields.
Paper refutes EM convergence theory and introduces a new EM algorithm.
problem The convergence theory of the EM algorithm is incorrect and affects its performance.
method Proposes a new EM algorithm called the Channel Matching (CM) EM algorithm and provides an initialization map.
result The locally maximal Q can affect the convergent speed but not the global convergence.
Study on regret minimization in deterministic MDPs.
problem Minimizing regret in deterministic reinforcement learning.
method Logarithmic regret lower bounds, leveraging graph theory and cycles.
result Explicitly quantifies the fundamental limit of performance achievable by any learning algorithm.
A graph bandit algorithm learns optimal paths on unknown graphs.
problem Optimal path selection on unknown graphs under uncertainty.
method G-UCB algorithm based on offline graph planning and optimism principle.
result Achieves tight regret bound of O ( ∣ S ∣ T log ( T ) + D ∣ S ∣ log T ) O(\sqrt{|S|T\log(T)}+D|S|\log T) O ( ∣ S ∣ T log ( T ) + D ∣ S ∣ log T ) . Unified theory of θ θ θ -expectations derived from chaotic dynamics.
problem Non-convex stochastic control problems outside G-expectations.
method Spectral theory of transfer operators for uniformly hyperbolic flows, viscosity solutions to HJB equations.
result Affine Hessian, non-convex gradient structure of θ θ θ -expectation. Risk measures applied to dynamic Markov processes with varying risk aversion.
problem Investigating dynamic risk measures in Markov decision processes with varying risk aversion.
method Distributional viewpoint on law-invariant convex risk measures, applied to Markov decision processes with latent costs and random actions.
result Existence of optimal policies in finite and infinite time horizons under mild assumptions.
Paper improves reinforcement learning efficiency with deterministic value gradients.
problem High sample complexity in model-free DDPG algorithms for continuous control tasks.
method Proposes DVG and DVPG algorithms with infinite horizon value gradients to improve sample efficiency.
result DVPG algorithm substantially outperforms state-of-the-art methods on continuous control benchmarks.
A large collection of financial contracts offering guaranteed minimum benefits are often posed as control problems, in which at any point in the solution domain, a control is able to take any one of an uncountable number of values from the admissible set. Often, such contracts specify that the holder exert control at a…
CGAN fails to improve deterministic sequence predictions, revealing a theoretical limitation.
problem Improving deterministic sequence predictions with CGAN.
method Developed an adversarial content loss approach.
result CGAN does not improve deterministic sequence predictions.
Bayesian MoE framework improves LLMs' uncertainty detection.
problem Brittleness and overconfidence in deterministic routing of LLMs.
method Structured Bayesian routing in weight-space, logit-space, and selection-space.
result Significant improvements in routing stability, calibration, and OoD detection.
We present the method of moments approach to pricing barrier-type options when the underlying is modelled by a general class of jump diffusions. By general principles the option prices are linked to certain infinite dimensional linear programming problems. Subsequently approximating those systems by finite dimensional …
Paper uses variational inference to estimate nonlinear models.
problem Parameter estimation for nonlinear state-space models.
method Variational inference approach for nonlinear state-space models.
result The method provides robust parameter estimates and outperforms alternatives.
We study the problem of option replication under constant proportional transaction costs in models where stochastic volatility and jumps are combined to capture the market's important features. Assuming some mild condition on the jump size distribution we show that transaction costs can be approximately compensated by …
Counterfactual learning improves SMT by smoothing out deterministic logs.
problem Deterministic logging limits exploration in SMT systems.
method Additive and multiplicative control variates to smooth out deterministic components.
result Improvements of up to 2 BLEU points achieved through counterfactual learning.
Paper combines deterministic and stochastic inference methods for PGMs.
problem Combining biases from deterministic methods and high costs from Monte Carlo.
method Sequential Monte Carlo algorithm that uses output from deterministic approximations.
result Improves upon deterministic methods and Monte Carlo by reducing biases and computational costs.