Refines deep generative models to improve data density precision.
problem Achieving precise representation of data probability density in deep models.
method Iterated generative modeling to refine latent space, addressing topological obstructions.
result Latent Space Refinement (LaSeR) protocol improves generative model precision.
Enhanced latent spaces improve collider simulation precision.
problem Improving the precision of collider physics simulations.
method Machine learning techniques including reweighting, pre-processing, and latent space refinement.
result Sub-percent precision across various phase spaces achieved.
UT module refines VAE latent space, improving disentanglement and interpretability.
problem Irregular latent distributions cause posterior collapse and misalignment in VAEs.
method UT module uses G-KDE clustering, GM modeling, and PIT to transform latent space into uniform distribution.
result UT module enhances disentanglement and interpretability of latent representations.
Spectral clustering with edge counting detects communities in sparse models.
problem Detecting communities in sparse latent space models.
method Spectral clustering followed by edge counting.
result Algorithm achieves consistency and optimality for a broad class of models.
Improved graph embedding through refined linear transformation and community recovery.
problem Identifying meaningful latent communities in graph data.
method Refined graph encoder embedding via linear transformation, self-training, and latent community recovery.
result Improved vertex embedding and better decision boundaries for vertex classification.
Improved neural image compression with refined latent representations.
problem Sub-optimal results from variational autoencoders due to imperfect optimization and capacity limitations.
method Stochastic Gumbel Annealing (SGA) and its extensions (SGA+), including three different methods.
result Significant improvement in compression performance, especially on the R-D trade-off.
Proposes a method to refine PDE-driven high-dimensional rare-event simulation.
problem Challenges in constructing accurate surrogates for rare-event simulation.
method Adaptive importance sampling framework that refines a locally constructed surrogate.
result Achieves accuracy comparable to true-model adaptive importance sampling with fewer high-fidelity evaluations.
Study evaluates interpretability of time series foundation models' latent spaces.
problem Improving interpretability of latent spaces in time series models for visual analytics.
method Evaluated MOMENT family of transformer-based models on five datasets, fine-tuning for performance.
result Fine-tuning improved latent space clarity but limited interpretability remained.
New framework transfers latent knowledge from weak to strong models.
problem Aligning superhuman LLMs with human feedback.
method Transfer learning framework using refinement approach.
result Proves weak-to-strong generalization is possible.
Paired autoencoders solve inverse problems using latent space projections.
problem Solving inverse problems in scientific computing.
method Paired autoencoder framework that projects data and quantity of interest into a latent space.
result Paired autoencoders generate multiple reconstruction metrics and enable latent-space refinement for accurate data fitting.
DDVI uses diffusion models for variational inference, improving latent variable model performance.
problem Improving variational inference in latent variable models.
method Introduces diffusion-based variational posteriors trained with a regularized ELBO.
result Outperforms alternative variational posteriors on various benchmarks and a biology task.
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.
ED-NeRF efficiently edits 3D scenes using latent space NeRF and improved loss functions.
problem Slow training speeds and inadequate editing loss functions in existing NeRF editing techniques.
method Embedding real-world scenes into latent space of LDM, using a unique refinement layer and an improved loss function.
result ED-NeRF achieves faster editing speed and improved output quality compared to state-of-the-art models.
We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine…
Algorithm recovers causal graphs in presence of latent confounders and selection bias.
problem Recovering causal graphs in the presence of latent confounders and selection bias.
method Iterative causal discovery (ICD) algorithm that relies on causal Markov and faithfulness assumptions.
result Sound and complete algorithm that recovers the equivalence class of the underlying causal graph.
AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing
problem Auditing LLM-as-a-Judge decisions
method Adaptive uncertainty-aware refinement
result Human-consistent signal learning and evidence propagation
Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructi…
Diffusion models generate music sequences without autoregressive loops.
problem Generating music sequences from symbolic data using diffusion models.
method Parameterize discrete symbolic data in continuous latent space, train diffusion model, generate sequences through reverse process.
result Strong unconditional generation and post-hoc conditional infilling compared to autoregressive models.
Latent factor models have achieved great success in personalized recommendations, but they are also notoriously difficult to explain. In this work, we integrate regression trees to guide the learning of latent factor models for recommendation, and use the learnt tree structure to explain the resulting latent factors. S…
Latent-IMH improves Bayesian inference for expensive operators.
problem Efficient sampling from posterior distributions in inverse problems with computationally expensive operators.
method Metropolis-Hastings independence sampler using approximate and exact operators.
result Latent-IMH outperforms existing methods in computational efficiency.
Tab-TRM uses recursive model for insurance pricing on tabular data.
problem Insurance pricing on tabular data.
method Adapts recursive latent reasoning to insurance modeling using a compact, parameter-efficient network.
result Improves insurance pricing accuracy using iterative refinement of latent tokens.
New inequality for refined knot invariants in a specific space.
problem General adjunction inequality for refined s-invariants does not hold. method Introduced an adjunction inequality for a specific spatial refinement in kCP2. result An adjunction inequality holds for the s-version of the Sq1-refinement in kCP2. Improves GAN sample quality by refining the training dataset.
problem GANs generate unrealistic samples outside the data manifold.
method Instance selection to improve sample quality and reduce training time.
result Significantly reduces training time and improves sample fidelity.
AGFN improves causal discovery by integrating expert feedback and handling latent confounding.
problem Inaccurate causal discovery due to unreliable expert knowledge and latent confounding.
method Ancestral GFlowNet (AGFN) is a reinforcement learning algorithm that iteratively refines a policy based on noisy expert feedback to infer ancestral graphs.
result AGFN converges to the true ancestral graph given accurate expert responses and outperforms baselines in structural Hamming distance and Bayesian Information Criterion.
Directed latent variable models that formulate the joint distribution as p(x,z)=p(z)p(x∣z) have the advantage of fast and exact sampling. However, these models have the weakness of needing to specify p(z), often with a simple fixed prior that limits the expressiveness of the model. Undirected latent variabl…
Dual-Channel Tensor Neural Network (DC-TNN) decomposes tensor data into low-rank and sparse components for better estimation and inference.
problem Tensor-valued data with multilinear dependencies are challenging to process due to loss of multiway geometry under vectorization.
method DC-TNN decomposes tensors into a low-rank core and a sparse refinement, processing them through coupled neural channels.
result Established non-asymptotic risk bounds and developed structure-aware conformal ROC and AUC confidence bands.
We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our β-TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art β-VAE objective for learning disentangled representations, requiring n…
Braverman and Kappeler introduced a refinement of the Ray-Singer analytic torsion associated to a flat vector bundle over a closed odd-dimensional manifold. We study this notion and improve the Braverman-Kappeler theorem comparing the refined analytic torsion with Farber-Turaev refinement of the combinatorial torsion. …
VSCOUT detects anomalies in high-dimensional data using a hybrid VAE approach.
problem Challenges in classical SPC for high-dimensional, non-Gaussian data.
method Hybrid VAE architecture with ARD prior, ensemble filtering, and changepoint detection.
result VSCOUT achieves superior sensitivity to special-cause structure and controlled false alarms.
We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space can exceed the observed dimensionality. In particular, we consider multiview mixtures, spherical Gaussian mixtures, ICA, and sparse coding models. We provide tight concentration…
Counting lattice points in moduli space of Klein surfaces.
problem Count lattice points in moduli space of Klein surfaces.
method Introduced metric Möbius graphs, counted lattice points weighted by non-orientability measure, deduced recursion for volumes.
result Proved refined version of Norbury's recursion and computed refined Euler characteristic.
Algorithm recovers causal graphs from data with fewer tests.
problem Recovering causal graphs from observational data with latent confounders and selection bias.
method Iterative CI tests with increasing condition set sizes.
result Significantly fewer CI tests and condition sets compared to FCI.
Improved hierarchical discrete VAEs for better stability and performance.
problem Training stable and efficient hierarchical discrete VAEs with numerous latent variables.
method Introducing Relaxed-Responsibility Vector-Quantisation to parameterise discrete latent variables in a hierarchical structure.
result Achieved state-of-the-art bits-per-dim results for various standard datasets.
An ADRC-incorporated SGD algorithm improves latent factor analysis speed and accuracy.
problem Slow convergence in standard SGD for HDI matrix analysis.
method Incorporates ADRC principles to refine historical and future learning error states.
result Empirically outperforms state-of-the-art LFA models in HDI matrix prediction.
A new method for math reasoning that allows for iterative correction.
problem Standard reasoning models commit to each token and cannot recover from early errors.
method Generative framework with latent thought vectors for iterative self-correction.
result 30 rethinking iterations surpass baselines with 15 times more parameters.
Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure among data points is available, previous work proposed Correlated Variational Auto-Encoders (CVAEs), which employ a structured mixture model as …
Generates consistent IV surfaces using VAEs and SDE models.
problem Creating arbitrage-free IV surfaces from historical data.
method Combining VAEs with SDE models for parameter distribution, sampling, and decoding.
result Superior out-of-sample performance of the refined VAE model.
Improved text-to-image alignment using iterative VQA feedback.
problem Misalignment between text prompts and generated images, especially for complex inputs.
method Decompose complex prompts into assertions, evaluate each using VQA, combine scores iteratively.
result Significantly higher correlation with human ratings compared to CLIP, BLIP scores.
Algorithm learns causal structures from time-series data, reducing tests for temporal vs. contemporaneous relations.
problem Learning causal structures from time-series data with latent confounders.
method Constraint-based algorithm that refines a causal graph by learning temporal relations first, then contemporaneous ones.
result Reduces the number of statistical tests and improves accuracy for synthetic and real-world data.
The paper refines classical covariance asymptotics using geometric information geometry.
problem Deviation of finite-sample behavior from classical predictions in curved models.
method Develops a curvature-aware refinement by viewing parametric families as Riemannian manifolds with Fisher-Rao metric.
result Derives an \(n^{-2}\) correction to the leading \(n^{-1}I(θ)^{-1}\) covariance term for score-root estimators.
Refines Hurwitz numbers with a two-parameter theory.
problem Understanding polynomial structure and tropicalization of b-Hurwitz numbers. method Introducing CJT-refinement of symmetric functions on Fock space.
result Derives tropicalization of b-Hurwitz numbers and solves an open problem. Accelerates pulsar light curve inference with learned representations and optimization.
problem Computational expense of Markov chain Monte Carlo methods for posterior inference.
method Combining U-Net latent representations with local simulator-guided optimization.
result 120x reduction in inference time (24 hours to 12 minutes) with accuracy preserved.
The concept of refinement from probability elicitation is considered for proper scoring rules. Taking directions from the axioms of probability, refinement is further clarified using a Hilbert space interpretation and reformulated into the underlying data distribution setting where connections to maximal marginal diver…
The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been demonstrated to select suboptimal variational parameters, often resulting in consi…
Scalable GPLVM reduces complexity in scRNA-seq data, accounting for technical and biological confounders.
problem Complexity and confounders in scRNA-seq data hamper interpretation.
method Extended Gaussian process latent variable model (GPLVM) to handle large datasets.
result Framework reconstructs latent signatures and captures disease-specific gene expression.
Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space interpolation, attribute vectors and concept vectors, among other things. We investigate …
This paper studies the problem of learning the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different domains, e.g., the output is a photo image and the input is a sketch image. We solve this problem by cooperative training of a fast thinking initial…
Describes the relationship between two spectral sequences and their joint refinement.
problem Computing the cohomology of a group or space using spectral sequences.
method Joint tri-graded refinement of the Leray--Serre and Eilenberg--Moore spectral sequences.
result One of the spectral sequences always degenerates from its second page, and the other satisfies a local-to-global property.