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.

168,657 papers · 148 categories

Trend · papers per month

152303455606 · Jun 202019922001200920172026
48 results for Latent Information Gain

CADD improves generative quality by augmenting discrete diffusion with continuous latent space.

problem Loss of semantic information between denoising steps in discrete diffusion models.
method Introduces a framework that augments discrete state space with a continuous latent space, allowing for graded, informative masked tokens.
result CADD improves generative quality across text generation, image synthesis, and code modeling.

New insights explain why ββ-VAEs fail at disentanglement.

problem Disentanglement performance of ββ-VAEs peaks at intermediate ββ and collapses as regularization increases.
method Formalized information-theoretic mechanism, introduced λβλβ-VAE to stabilize disentanglement.
result Strong regularization pressure leads to mutual information collapse in ββ-VAEs.

This paper treats prediction markets as Bayesian inverse problems to quantify uncertainty and identify event outcomes.

problem Uncertainty and identifiability in prediction market outcomes from price-volume histories.
method Formulates prediction markets as Bayesian inverse problems, introduces a log-odds observation model, and derives posterior uncertainty quantification and identifiability criteria.
result Explicit diagnostics for informative and stable inference regimes, and validation through synthetic data experiments.

New BED method handles online inference for partially observed dynamical systems.

problem Optimizing data collection for partially observable, partially online dynamical systems.
method Derived estimators of expected information gain and its gradient for SSMs, using nested particle filters.
result Successfully handles both partial observability and online inference in realistic models.

INP accelerates stochastic simulations using deep Bayesian active learning.

problem Computational expense of stochastic simulations at fine-grained resolution.
method Interactive Neural Process (INP) framework combining spatiotemporal surrogate model and active learning acquisition function.
result STNP outperforms baselines in accelerating stochastic simulations and LIG achieves state-of-the-art for Bayesian active learning.

Information theory provides a mathematical foundation to measure uncertainty in belief. Belief is represented by a probability distribution that captures our understanding of an outcome's plausibility. Information measures based on Shannon's concept of entropy include realization information, Kullback-Leibler divergenc…

2019-11-21abs ↗pdf ↗

Meta-active learning optimizes control of safety-critical systems by efficiently learning dynamics and configurations.

problem Efficiently learning system dynamics and optimal configurations for safety-critical systems like deep brain stimulation.
method Meta-learning an acquisition function using LSTM, cast as meta-learning, with a mixed-integer linear program policy.
result Achieved a 46% increase in information gain and a 20% speedup in computation time over baselines.

Unified framework for hybrid learning and optimization via active inference.

problem Sequential decisions in black-box evaluations requiring both task improvement and uncertainty reduction.
method Pragmatic Curiosity (PraC) framework that evaluates queries by balancing information gain and pragmatic value.
result Unified approach reduces decision risk and improves coverage of critical regions without task-specific rules.

Bayesian active learning reduces data needed for latent variable models.

problem Active learning for latent variable models, especially mixtures of linear regressions and HMMs with GLM observations.
method Maximum-mutual-information input selection for discrete latent variable regression models.
result Active learning can achieve large gains for mixtures of linear-Gaussian models and substantially reduces data needed for GLM-HMM.

Introduces relative information gain for improving Gaussian process regression rates.

problem Improving the sample complexity of estimating or maximizing unknown functions.
method Introduces relative information gain, interpolates between effective dimension and information gain, and proves PAC-Bayesian bounds.
result Obtains minimax-optimal rates of convergence through the relative information gain.

IntroVAC learns interpretable latent subspaces for better image quality.

problem Difficulties in interpreting latent spaces and limitations in image generation.
method Introspective Variational Classifier (IntroVAC) using additional labels and adversarial training.
result Improved image quality and meaningful latent directions for fine-grained manipulation.

GAME improves matrix completion by considering subgroup-specific latent structures.

problem Heterogeneous data with overlapping categories, smoothing away subgroup-specific variation.
method Group-Aware Matrix Estimation (GAME) with overlapping nuclear-norm penalties.
result GAME outperforms global low-rank estimators in structured missingness regimes.

Proposes a framework to handle missing data in traffic forecasting with sensor blackouts.

problem Missing data in traffic forecasting due to sensor blackouts, especially when correlated with traffic conditions.
method Latent state-space framework that models traffic dynamics and sensor dropout probabilities.
result Improves traffic forecasting by reducing blackout imputation RMSE from 7.02 to 4.23, with MNAR modeling providing additional gains.

Paper presents new algorithms for causal discovery with latent variables and overlapping datasets.

problem Causal discovery with latent variables and overlapping datasets.
method Introduces tiered FCI and tIOD algorithms for constraint-based causal discovery.
result The tIOD algorithm is more efficient and informative than the IOD algorithm.

New method improves causal discovery in time series with latent confounders.

problem Low recall in causal discovery for autocorrelated time series with latent confounders.
method Iterative procedure that includes causal parents in conditioning sets, using novel orientation rules.
result Significantly higher recall compared to existing methods, especially in strong autocorrelation cases.

A new model integrates covariates with grade of membership analysis for better latent structure recovery.

problem Improving latent structure recovery in multivariate categorical data analysis.
method Covariate-assisted grade of membership model exploiting shared low-rank simplex geometry.
result Auxiliary covariates can provably improve latent structure recovery, leading to faster convergence rates.

Eluder dimension and information gain are equivalent for reproducing kernel Hilbert spaces.

problem Complexity measures in bandit and reinforcement learning.
method Equivalence of eluder dimension and information gain for reproducing kernel Hilbert spaces.
result Eluder dimension and information gain are equivalent for reproducing kernel Hilbert spaces.

BITS for GAPS uses Bayesian methods to improve surrogate model accuracy in complex systems.

problem Improving surrogate model accuracy in complex physical systems with uncertainty.
method Bayesian Information-Theoretic Sampling for hierarchical Gaussian Process Surrogates.
result Increased expected information gain and predictive accuracy by targeting high-uncertainty regions.

New approach categorizes objective functions for embodied agents.

problem Understanding how objectives relate to each other and discovering new objectives.
method Introducing Action Perception Divergence (APD) to categorize objective functions.
result Introduces a spectrum of objectives from narrow to general, explaining various unsupervised objectives.

Adaptive framework for learning latent space dimensions in GANs.

problem Inadequate latent space dimensions lead to poor generative models for complex data.
method Proposes a novel framework (LWGAN) that adaptively learns latent dimensions of data manifolds.
result Proves that the estimated intrinsic dimension is a consistent estimate of the true data manifold dimension.

Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does not marginalize over latent alignments in a probabilistic sense. This property …

2018-07-10abs ↗pdf ↗

Proposes a new method to enhance neural learning by maximizing information gain.

problem Improving neural learning by selecting key variables to maximize information gain.
method Adaptive Ensemble Kalman Filter to quantify uncertainty and maximize information gain.
result The proposed method enables the neural network to learn more effectively from stochastic systems.

Proposes using equivariant generative models for compressed sensing with unknown orientations.

problem Recovering signals with unknown orientations from underdetermined systems of linear measurements.
method Equivariant variational autoencoder as a generative prior for compressed sensing.
result Signals with unknown orientations can be recovered using iterative gradient descent on the latent space of equivariant models.

Top2Vec finds topic vectors from documents and words without needing stop words or custom settings.

problem Topic modeling weaknesses, including needing known topics, stop words, and custom settings.
method Joint document and word semantic embedding to find topic vectors automatically.
result Top2Vec finds more informative and representative topics than probabilistic models.

ICYM2I corrects missingness bias in multimodal learning.

problem Missingness patterns between source and target environments affect multimodal learning performance.
method ICYM2I uses inverse probability weighting to correct missingness bias in predictive performance and information gain.
result ICYM2I improves multimodal learning performance by accounting for missingness.

New framework learns disentangled causal representations from observed labels.

problem Learning meaningful disentangled causal representations from observed data.
method ICM-VAE framework using flow-based diffeomorphic functions and causal disentanglement prior.
result Induces highly disentangled causal factors and improves robustness.

Active inference selects actions to maximize information gain, aiding structure learning.

problem Learning the structure of underlying world models.
method Active inference selects actions based on expected free energy, which includes information gain and value.
result Actions that maximize information gain help disambiguate among alternative models.

Proposes a framework to maximize mutual information in VAE models for better latent code representation.

problem Lack of explicit measurement of the quality of learned representations in VAE models.
method Variational Mutual Information Maximization Framework for VAE.
result Maximizes mutual information between latent codes and observations, improving latent code representation.

Proposes EPIG for active learning to improve predictive performance.

problem Suboptimal predictive performance of traditional active learning methods.
method Introduces EPIG, a new acquisition function measuring information gain in the space of predictions.
result EPIG leads to stronger predictive performance compared to BALD across various datasets and models.

We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction. We present new online algorithms for path learning with non-additive count-based gains for the three settings of full information, semi-bandit and…

2018-04-18abs ↗pdf ↗

Expands Bayesian experiment design framework to account for model discrepancies.

problem Model misspecification in Bayesian optimal experiment design.
method Introduces Expected General Information Gain and Expected Discriminatory Information criteria.
result Demonstrates improved robustness and detection capabilities in experiment design.

This paper introduces a new member of the family of Variational Autoencoders (VAE) that constrains the rate of information transferred by the latent layer. The latent layer is interpreted as a communication channel, the information rate of which is bound by imposing a pre-set signal-to-noise ratio. The new constraint s…

2018-07-19abs ↗pdf ↗

Active inference minimizes expected free energy for optimal behavior.

problem Understanding and optimizing behavior in complex systems.
method Combines Bayesian decision theory, optimal Bayesian design, and the free energy principle.
result Active inference emerges as a unified framework for information-seeking, utility maximization, and goal-directed behavior.

Active sampling algorithm improves accuracy of inferred scores from pairwise comparisons.

problem Inference of accurate scores from time-consuming pairwise comparisons.
method Approximate message passing and expected information gain maximization.
result ASAP offers the highest accuracy of inferred scores compared to existing methods.

New method improves robustness of Bayesian experimental design.

problem Bayesian experimental design's sensitivity to prior distribution changes.
method Introduces robust expected information gain (REIG) and uses KL-divergence ambiguity sets.
result REIG stabilizes sampling-based EIG estimation and compensates for prior variability.

FisherSFT selects informative examples to fine-tune LLMs efficiently.

problem Adapting large language models to new domains efficiently.
method Selects examples maximizing information gain using Hessian of log-likelihood.
result Empirically demonstrates improved performance with reduced computational cost.

New method neutralizes gender bias in word embeddings without losing semantic information.

problem Gender biases in word embeddings trained on human-generated corpora.
method Latent Disentanglement and Counterfactual Generation with siamese auto-encoder and gradient reversal layer.
result Our method outperforms existing debiasing methods in preserving semantic information and neutralizing gender biases.

New method corrects active learning for distribution shifts and outliers.

problem Conventional active learning methods fail to account for test-time distribution.
method JEPIG, a hybrid of BALD and EPIG, maximizes expected predictive information gain.
result JEPIG outperforms conventional methods in active learning with distribution shifts.