A novel framework refines diffusion models iteratively for better downstream reward optimization.
problem Optimizing reward functions during inference of diffusion models.
method Iterative refinement process with noising and reward-guided denoising steps.
result Superior empirical performance in protein and DNA design.
Refines neural network predictions using background knowledge for improved accuracy.
problem Compensate for lack of labeled data in neural networks.
method Introduces differentiable refinement functions and Iterative Local Refinement (ILR) algorithm to refine predictions efficiently and accurately.
result ILR finds competitive results in MNIST addition task and refines predictions on complex SAT formulas.
GENESIS-V2 infers unordered object representations without iterative refinement.
problem Unsupervised learning of unordered object representations for complex images.
method Stochastic stick-breaking process for clustering pixel embeddings.
result GENESIS-V2 outperforms recent baselines in unsupervised image segmentation and scene generation.
LARA forecasts financial asset trends by refining noisy labels and extracting profitable samples.
problem Low signal-to-noise ratio and stochastic nature of financial data lead to poor predictions.
method LARA combines LA-Attention and RA-Labeling to refine and extract profitable samples.
result LARA significantly outperforms existing methods on Qlib platform.
To improve the compressive sensing MRI (CS-MRI) approaches in terms of fine structure loss under high acceleration factors, we have proposed an iterative feature refinement model (IFR-CS), equipped with fixed transforms, to restore the meaningful structures and details. Nevertheless, the proposed IFR-CS still has some …
Variational methods that rely on a recognition network to approximate the posterior of directed graphical models offer better inference and learning than previous methods. Recent advances that exploit the capacity and flexibility in this approach have expanded what kinds of models can be trained. However, as a proposal…
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 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.
Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection. But, they do not work well with objects of multiple scales. To overcome such a limitation, in this work, we propose a recurrent attentional convolutional-deconvolution network (RACDNN). Using spatial transformer and recurrent …
Refines online learning to rank algorithm with tighter bounds.
problem Online learning to rank in machine learning.
method Utilized method of mixtures and asymptotic expansions to refine inequalities.
result Improved algorithm and performance estimation.
Improved image generation through iterative flow matching to reduce hallucinations.
problem Hallucinations in image generation models.
method Iterative flow matching to refine and correct paths in generative models.
result Enhanced generative modeling with reduced unrealistic images.
We propose a black-box variational inference method to approximate intractable distributions with an increasingly rich approximating class. Our method, termed variational boosting, iteratively refines an existing variational approximation by solving a sequence of optimization problems, allowing the practitioner to trad…
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.
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.
IterefinE combines KG refinement with embeddings to improve KG quality.
problem Noisy Knowledge Graphs lead to poor performance in downstream tasks.
method Iterative KG refinement using embeddings and inference rules.
result Improved KG refinement leading to higher F1 scores.
ICR speeds up GP modeling on unevenly spaced data.
problem High computational complexity of exact GP inference.
method Iterative Charted Refinement (ICR) for sparse, nearly arbitrary data.
result ICR achieves comparable accuracy to state-of-the-art methods but at a much faster computational speed.
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.
This paper refines the Gaussian Sinkhorn algorithm for general multivariate models.
problem Finite-dimensional solutions for general Gaussian multivariate models.
method Recursive formulation of the Sinkhorn algorithm for Gaussian models, including closed form expressions of entropic transport maps and Schrödinger bridges.
result Refined convergence analysis of Gaussian Sinkhorn algorithms.
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.
This study develops a NURBS-based method for conformal surface flattening without singularities.
problem Flatten surfaces conformally without singularities.
method NURBS-based approach with iterative refinement of input and flattening surfaces, leveraging nonlinear extension of VarPro.
result Developed a singularity-free NURBS-based method for conformal surface flattening.
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
Study finds differences in LTs across tasks and architectures, proposing a consensus-based method for generating refined lottery tickets.
problem Understanding the variability and uniqueness of Lottery Tickets across different image classification tasks and architectures.
method 28 combinations of image classification tasks and architectures, iterative pruning techniques, consensus-based method for generating refined lottery tickets.
result Disproves the uniqueness of Lottery Tickets and connects emergent mask structure to the choice of pruning.
Quantizes symplectic fibrations to analyze vector bundles and metrics.
problem Quantizing higher rank vector bundles and understanding their metrics.
method Relates Berezin-Toeplitz quantization to hybrid systems and symplectic fibrations.
result Established refined estimates for computing balanced metrics on Kähler manifolds.
WaveGrad generates high-fidelity audio using gradient estimation.
problem Generating high-fidelity audio efficiently.
method Conditional model using score matching and diffusion models, iteratively refining a Gaussian white noise signal.
result WaveGrad can generate high-fidelity audio samples using as few as six iterations.
Self-guiding diffusion models improve time series forecasting, refinement, and generation.
problem Improving time series forecasting, refinement, and generation.
method Unconditionally-trained diffusion model with self-guidance mechanism.
result TSDiff outperforms task-specific conditional forecasting methods and maintains generative performance.
MaxMax Q-Learning improves coordination in multi-agent reinforcement learning by refining action selection.
problem Relative over-generalization in decentralized multi-agent reinforcement learning.
method MaxMax Q-Learning employs iterative sampling and evaluation of potential next states to refine approximations of ideal state transitions.
result MaxMax Q-Learning frequently outperforms existing baselines, demonstrating enhanced convergence and sample efficiency.
Gradient descent with small random init mimics spectral methods for low-rank matrix recovery.
problem Reconstructing a low-rank matrix from few measurements.
method Gradient descent with small random initialization followed by a few iterations.
result Gradient descent from small random init converges to a well-generalizing solution.
We proof existence theorems for the Dirichlet problem for hypersurfaces of constant special Lagrangian curvature in Hadamard manifolds. The first results are obtained using the continuity method and approximation and then refined using two iterations of the Perron method. The a-priori estimates used in the continuity m…
Study Kähler-Einstein potentials on stable varieties near singularities
problem Asymptotic behavior of Kähler-Einstein potentials on stable varieties near singularities
method Using iterated logarithmic functions and refined lower bounds
result Improved estimates for Kähler-Einstein potentials
In this letter, we address sparse signal recovery using spike and slab priors. In particular, we focus on a Bayesian framework where sparsity is enforced on reconstruction coefficients via probabilistic priors. The optimization resulting from spike and slab prior maximization is known to be a hard non-convex problem, a…
SLHF uses sequential game theory to optimize preferences from human feedback.
problem Optimizing preferences from human feedback in sequential settings.
method SLHF frames the problem as a sequential-move game between Leader and Follower, decomposing the optimization into refinement and adversarial optimization.
result SLHF achieves strong alignment across diverse preference datasets and scales to large models.
The paper introduces a multilevel initialization method for deep neural networks.
problem Training very deep neural networks with layer-parallel methods.
method Continuous interpretation of training as optimal control, using time-dependent ODEs for neural network discretization, and a refinement strategy across the time domain.
result The method creates deep networks with good initializations from coarser networks, reducing training time and providing regularization.
We give improved algorithms for the ℓp-regression problem, minx∥x∥p such that Ax=b, for all p∈(1,2)∪(2,∞). Our algorithms obtain a high accuracy solution in O~p(m2p+∣p−2∣∣p−2∣)≤O~p(m31) iterations, where each iteration requires s…
A neural architecture learns and refines graph correspondences.
problem Learning structural correspondences between graphs.
method Two-stage neural architecture: node embeddings followed by message passing networks.
result Message passing scheme computes well-founded consensus for corresponding neighborhoods.
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…
We give a new geometric obstruction to the iterated Bing double of a knot being a slice link: for n>1 the (n+1)-st iterated Bing double of a knot is rationally slice if and only if the n-th iterated Bing double of the knot is rationally slice. The main technique of the proof is a covering link construction simplifying …
Optimal learning rate schedules derived for various tasks.
problem Inadequate learning rate schedules in practice compared to theory.
method Refined analysis of learning rate schedules for optimization algorithms.
result Derives new problem-adaptive learning rate schedules.
The iterative nature of the expectation maximization (EM) algorithm presents a challenge for privacy-preserving estimation, as each iteration increases the amount of noise needed. We propose a practical private EM algorithm that overcomes this challenge using two innovations: (1) a novel moment perturbation formulation…
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.
Estimate arrival times in random recursive trees using iterated Jordan centralities.
problem Estimate arrival times in random recursive trees.
method Pointwise approach using iterated Jordan centralities.
result Tail bounds for relative estimation error.
Graph refinement, or the task of obtaining subgraphs of interest from over-complete graphs, can have many varied applications. In this work, we extract trees or collection of sub-trees from image data by, first deriving a graph-based representation of the volumetric data and then, posing the tree extraction as a graph …
AIHT improves online high-dimensional quantile regression by separating support discovery and refinement.
problem Online high-dimensional quantile regression with structural sparsity.
method Adaptive Iterative Hard Thresholding (AIHT) alternates stochastic updates with adaptive hard-thresholding steps.
result AIHT achieves logarithmic regret for the sliding-window objective in high-dimensional settings.
Molecule optimization is about generating molecule Y with more desirable properties based on an input molecule X. The state-of-the-art approaches partition the molecules into a large set of substructures S and grow the new molecule structure by iteratively predicting which substructure from S to add. However, s…
A new method for estimating large-scale linear models with improved precision.
problem Estimating large-scale linear statistical models efficiently.
method Sequential Least-Squares Estimators with Fast Randomized Sketching (SLSE-FRS), integrating Sketch-and-Solve and Iterative-Sketching methods.
result SLSE-FRS produces high-precision estimators, outperforming state-of-the-art methods.
We use a cluster ensemble to determine the number of clusters, k, in a group of data. A consensus similarity matrix is formed from the ensemble using multiple algorithms and several values for k. A random walk is induced on the graph defined by the consensus matrix and the eigenvalues of the associated transition proba…
Unified framework for AMP iterations using graph indexing.
problem Complex high-dimensional statistical inference problems.
method Graph-based indexing of AMP iterations, modular proof of state evolution.
result Unified SE equations for AMP iterations indexed by graphs.
DP-SEP privatizes EP by refining a single factor per data point.
problem Private inference of complex models with limited memory.
method Stochastic Expectation Propagation with differential privacy.
result DP-SEP provides better posterior estimates with guaranteed privacy.
We re-derive Manolescu's unoriented skein exact triangle for knot Floer homology over F_2 combinatorially using grid diagrams, and extend it to the case with Z coefficients by sign refinements. Iteration of the triangle gives a cube of resolutions that converges to the knot Floer homology of an oriented link. Finally, …