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.

168,695 papers · 148 categories

Trend · papers per month

2985968931,191 · Jun 202019922001200920172026
48 results for latent space optimization

LOL-BO improves latent space Bayesian optimization over structured inputs.

problem Optimizing complex functions over high-dimensional, structured search spaces.
method Adapting trust regions from high-dimensional to structured settings, using a DAE to map inputs into a latent space.
result Achieves up to 20x improvement over state-of-the-art methods.

NLGS optimizes latent geometry for better model performance.

problem Improving machine learning model performance by aligning latent space geometry with data structure.
method NLGS uses product manifolds with Gromov-Hausdorff distance for latent geometry search.
result NLGS finds optimal latent geometry with query-efficient Bayesian optimization.

AMES framework selects optimal embedding space for latent graph inference.

problem No principled method for choosing the best embedding space for latent graph inference.
method Differentiable AMES framework using backpropagation to select optimal embedding space.
result Consistently achieves comparable or superior results across multiple datasets.

This paper shows how to estimate distances in latent space of random graphs using entropic OT.

problem Estimating distances between groups of nodes in latent space of random graphs.
method Entropic Optimal Transport (OT) with stability results for perturbations of the cost matrix.
result Consistent estimation of entropic OT distances between groups of nodes in latent space.

Improved method for efficient black-box optimization in latent space.

problem Efficiently optimize expensive black-box functions over complex input spaces.
method Optimize in latent space of deep generative models, retrain model periodically and weight data points.
result Significantly improved efficiency and performance on synthetic and real-world problems.

LGS-Net improves NCO performance on combinatorial optimization tasks.

problem NP-hard combinatorial optimization problems in logistics, manufacturing, and drug discovery.
method LGS-Net uses a latent space model that conditions on problem instances and introduces Latent Guided Sampling for efficient inference.
result Empirical results show state-of-the-art performance on benchmark routing tasks.

Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter spaces in extreme low-data regimes. We show that it is possible to bypass these …

2018-07-16abs ↗pdf ↗

LES reduces over-exploration in LSO, improving solution quality.

problem Over-exploration in LSO leads to unrealistic solutions.
method LES uses a decoder's approximation of the data distribution to mitigate over-exploration.
result LES enhances solution quality while maintaining high objective values.

This research examines the geometry of latent spaces in push-forward generative models.

problem Tendency of deep generative models to output samples outside target distribution support.
method Geometric measure theory and truncation method to enforce simplicial cluster structure.
result Proves sufficient condition for optimality in latent space geometry.

Paper introduces Latent-CLIP for efficient text-image comparison in latent space.

problem Efficiently compare text and images in latent space without costly decoding.
method Trains CLIP model in latent space, uses Latent-CLIP rewards for noise optimization, and guides generation away from harmful content.
result Latent-CLIP matches CLIP performance on text-image classification and harmful content detection.

The paper develops a method to dynamically adjust VAE latent space dimensions during training.

problem Under- or overprovisioning of latent space dimensions in VAEs.
method GECO optimizer with L0L_0-ARM gradient estimator to dynamically adjust latent space dimensions.
result The latent space can be pruned effectively without violating reconstruction error constraints.

Generative Latent Implicit Conditional Optimization (GLICO) learns from small samples.

problem Learning from small labeled datasets.
method Generative Latent Implicit Conditional Optimization (GLICO) learns a latent space and generator from small labeled data.
result GLICO synthesizes new samples for every class using as few as 10 examples per class.

Variational Auto-Encoders enforce their learned intermediate latent-space data distribution to be a simple distribution, such as an isotropic Gaussian. However, this causes the posterior collapse problem and loses manifold structure which can be important for datasets such as facial images. A GAN can transform a simple…

2018-09-16abs ↗pdf ↗

Efficient RL in large POMDPs with latent determinism and embeddings.

problem Efficient reinforcement learning in large-scale POMDPs with latent states and observations.
method Conditional Hilbert space embeddings, linear optimal QQ-function, deterministic latent transitions, gap assumption.
result Computationally and statistically efficient algorithm for exact optimal policy.

Optimizes latent space of VAEs using decoder uncertainty to generate valid objects.

problem Lack of robustness in optimizing VAE latent space for black-box properties.
method Importance sampling-based estimator of decoder epistemic uncertainty to guide optimization.
result Improves trade-off between black-box objective and validity of generated samples.

NES optimizes discrete structured VAEs effectively without gradient propagation.

problem Learning high-dimensional discrete latent spaces in generative models.
method Natural Evolution Strategies (NES) for gradient-free optimization of discrete structures.
result NES effectively optimizes discrete structured VAEs, comparable to gradient-based methods.

This study rethinks the latent space in generative modeling, improving performance with less complex models.

problem Determining the optimal latent space for generative models and understanding its impact on model complexity.
method Proposed a new distance metric between latent and data distributions, and a two-stage training strategy called Decoupled Autoencoder (DAE).
result Improves generative performance with less complex models, as shown by comprehensive experiments on various models.

New method compresses facial videos using GANs and latent space optimization.

problem Efficiently compressing facial videos at low bit rates.
method Leverages StyleGAN for latent space representation and compression, learns optimal compression through entropy model and perceptual loss.
result Significantly reduces perceptual distortion at low bit rates compared to state-of-the-art codecs.

Optimizes variational inference for dynamic network models.

problem Estimating pairwise inner products and intercepts in dynamic latent space models.
method Structured mean-field variational inference with block coordinate ascent algorithm.
result Variational risk attains minimax optimal rate with logarithmic factor under certain conditions.

Automatic Chemical Design is a framework for generating novel molecules with optimized properties. The original scheme, featuring Bayesian optimization over the latent space of a variational autoencoder, suffers from the pathology that it tends to produce invalid molecular structures. First, we demonstrate empirically …

2017-09-16abs ↗pdf ↗

New algorithm infers trajectories from partial observations using optimal transport.

problem Inferring trajectories from partial observations of coupled systems.
method Extends MFL algorithm to latent SDEs using observable state space models and partial observations.
result Experiments show significant outperformance over latent-free baseline.

Generative AutoEncoders require a chosen probability distribution in latent space, usually multivariate Gaussian. The original Variational AutoEncoder (VAE) uses randomness in encoder - causing problematic distortion, and overlaps in latent space for distinct inputs. It turned out unnecessary: we can instead use determ…

2018-11-12abs ↗pdf ↗

Generative Adversarial Networks (GAN) training process, in most cases, apply Uniform or Gaussian sampling methods in the latent space, which probably spends most of the computation on examples that can be properly handled and easy to generate. Theoretically, importance sampling speeds up stochastic optimization in supe…

2019-10-06abs ↗pdf ↗

A new approach predicts next observations without explicit decoding for better control.

problem High-dimensional observations and unknown dynamics in real-world control tasks.
method Proposes a novel information-theoretic LCE approach using predictive coding to develop a decoder-free model.
result The model reliably learns a controllable latent space leading to superior performance.

A new gradient estimator reduces variance near boundaries for binary latent variables.

problem Explosive gradient variance near boundaries in binary latent variable models.
method Introduces a new gradient estimator (bitflip-1) and an aggregated estimator (UGC) that uses either bitflip-1 or DisARM for each coordinate.
result UGC has uniformly lower variance than DisARM and achieves optimal optimization objectives.

Bayesian optimization tackles mixed discrete-continuous problems with Gaussian processes.

problem Optimizing problems with both discrete and continuous variables using costly simulations.
method Relaxing discrete variables into continuous latent variables, using Bayesian optimization, and incorporating compatibility constraints with Lagrangians.
result Comparative analysis of different mixed Bayesian optimization approaches.

Optimal model selection for forecasting large collections of short time series using latent space.

problem Challenges in choosing among multiple forecasting methods for large, high-dimensional time series with limited data.
method Combining low-rank temporal matrix factorization with optimal model selection using cross-validation.
result Forecasting latent factors leads to significant performance gains compared to direct uni-variate model application.

This paper provides statistical guarantees for WAE's latent space regeneration.

problem Lack of statistical analysis for Autoencoders, especially WAE.
method Utilizes Vapnik Chervonenkis (VC) theory and Optimal Transport of measures under the Wasserstein metric.
result WAE achieves the target distribution in the latent space and regenerates the input distribution.

A popular approach for predicting the future of dynamical systems involves mapping them into a lower-dimensional "latent space" where prediction is easier. We show that the information-theoretically optimal approach uses different mappings for present and future, in contrast to state-of-the-art machine-learning approac…

2019-02-09abs ↗pdf ↗

Unified approach to DP problems using Gumbel distribution and variational Bayesian inference.

problem Solving classical optimal path problems in a probabilistic framework.
method Gumbel distribution and variational Bayesian inference for latent optimal paths.
result Unified approach transforms DP problems into directed acyclic graphs with Gibbs distribution.

This work improves disentanglement in latent space models without sacrificing generation quality.

problem Trade-off between disentanglement and generation quality in latent space models.
method Manifold optimization with a sum of autoencoder and PCA reconstruction errors, on the Stiefel manifold.
result Improves disentanglement without sacrificing generation quality.

This paper proposes a method to improve VAEs by extracting latent spaces from pre-trained diffusion models.

problem VAEs struggle with generating high-quality images due to unrealistic Gaussian assumptions.
method Optimizes an encoder to maximize marginal data log-likelihood and derives a decoder analytically.
result The method enhances VAE performance by discarding Gaussian assumptions and training a separate decoder network.