Doubly-stochastic normalization improves robustness to heteroskedastic noise.
problem Robustness to heteroskedastic noise in affinity matrix construction.
method Doubly-stochastic normalization of the Gaussian kernel.
result Doubly-stochastic normalization converges to clean matrix with rate m−1/2 under heteroskedastic noise. Woodbury transformations improve deep generative models with efficient invertibility and determinant calculation.
problem Efficiently invertible and determinant-calculable functions for deep generative models.
method Introducing Woodbury transformations that leverage matrix identities for efficient invertibility and determinant calculation.
result Woodbury transformations enable high-dimensional interactions, efficient sampling, and likelihood evaluation, outperforming other flow architectures.
New method estimates mutual information using normalizing flows.
problem Mutual information estimation in high-dimensional data.
method Normalizing flows to map data to target distributions with known MI.
result Theoretical guarantees and practical advantages demonstrated.
The estimation of normalizing constants is a fundamental step in probabilistic model comparison. Sequential Monte Carlo methods may be used for this task and have the advantage of being inherently parallelizable. However, the standard choice of using a fixed number of particles at each iteration is suboptimal because s…
Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep Q-learning, DQL) is assumed to be an appropriate algorithm to solve the demand-aware inter-slice resource management issue in network slicing by regarding the …
The normalized maximized likelihood (NML) provides the minimax regret solution in universal data compression, gambling, and prediction, and it plays an essential role in the minimum description length (MDL) method of statistical modeling and estimation. Here we show that the normalized maximum likelihood has a Bayes-li…
Bayesian inference for expensive likelihoods using Langevin Monte Carlo with NF.
problem Sampling from complex posterior distributions with expensive likelihoods.
method Deterministic Langevin equation with NF gradient, Metropolis-Hastings updates.
result Competitive performance compared to state-of-the-art methods.
Deep learning improves GW signal detection efficiency and robustness.
problem Traditional matched-filtering techniques are limited in detecting new GW signals.
method Optimized CNN models with techniques like batch normalization and dropout.
result CNN models are robust to the variation of GW waveform parameters.
New algorithm tackles nonconvex machine learning problems with adaptive normalization and independent sampling.
problem Nonconvex machine learning problems with generalized-smoothness.
method Adaptive gradient normalization, independent sampling, and gradient clipping.
result Achieves an O(ε^(-4)) sample complexity for fast convergence.
Improves NF for complex data distributions with multiple modes.
problem Difficulty in handling data distributions with multiple isolated modes.
method Proposes a new framework using variational latent representation to improve NF.
result Significantly more powerful for generating data distributions with multiple modes.
Globally normalized neural sequence models are considered superior to their locally normalized equivalents because they may ameliorate the effects of label bias. However, when considering high-capacity neural parametrizations that condition on the whole input sequence, both model classes are theoretically equivalent in…
This paper improves normalizing flows by combining MLE and sliced-Wasserstein distance for better data fidelity.
problem Normalizing flows struggle with generating realistic data and detecting out-of-distribution data.
method Proposes a hybrid objective function combining MLE and sliced-Wasserstein distance.
result Shows better generative abilities and lower likelihood of out-of-distribution data.
Complete normal forms for specific real hypersurfaces in complex space are constructed.
problem Constructing complete normal forms for real hypersurfaces in C3. method Utilizing equivariant moving frames for systematic symbolic manipulation.
result Complete normal forms for 5-dimensional real hypersurfaces in C3 are found. SPO optimizes LLMs by eliminating group-based baselines and variance issues.
problem Frequent degenerate groups and synchronization barriers in group-based policy optimization methods.
method Single-stream Policy Optimization (SPO) replaces per-group baselines with a persistent, KL-adaptive value tracker and global advantage normalization.
result SPO converges more smoothly and attains higher accuracy than GRPO, improving maj@32 by +3.4 pp across five math benchmarks.
FF algorithm uses goodness as a likelihood-ratio test for scalar normalization.
problem Training each layer locally with scalar goodness.
method FF algorithm uses a likelihood-ratio test with squared goodness as the sufficient statistic.
result The FF algorithm generalizes to anisotropic and heavy-tailed populations.
A new method improves generative models by learning lower-dimensional representations.
problem Normalizing flows cannot learn lower-dimensional representations of data.
method Noisy injective flows (NIF) that map latent space to a learnable manifold in high-dimensional data space using injective transformations and an additive noise model.
result Simple application of NIF to existing flow architectures significantly improves sample quality and yields separable data embeddings.
This paper proposed a bias-compensated normalized maximum correntropy criterion (BCNMCC) algorithm charactered by its low steady-state misalignment for system identification with noisy input in an impulsive output noise environment. The normalized maximum correntropy criterion (NMCC) is derived from a correntropy based…
This paper develops a slice sampler for Bayesian linear regression models with arbitrary priors. The new sampler has two advantages over current approaches. One, it is faster than many custom implementations that rely on auxiliary latent variables, if the number of regressors is large. Two, it can be used with any prio…
Paper proposes a debiased estimator for adaptive linear regression.
problem Non-normal asymptotic behavior of OLS estimator in adaptive linear regression.
method Adaptive linear estimating equations to construct debiased estimator.
result Established asymptotic normality of the debiased estimator.
Proposes group whitening to enhance deep learning models' performance.
problem Improving learning efficiency and representational capacity in deep learning models.
method Group Whitening (GW) combines whitening and group normalization to balance these aspects.
result Group Whitening consistently improves model performance across different architectures and benchmarks.
We present sparse topical coding (STC), a non-probabilistic formulation of topic models for discovering latent representations of large collections of data. Unlike probabilistic topic models, STC relaxes the normalization constraint of admixture proportions and the constraint of defining a normalized likelihood functio…
Batch normalization with regularization turns deterministic autoencoders into generative models.
problem Creating generative models from deterministic autoencoders.
method Using batch normalization as a source of non-determinism and adding entropic regularization.
result Deterministic autoencoders can be transformed into generative models with similar performance to variational autoencoders.
Efficiently computes optimal transport maps and Wasserstein barycenters using conditional normalizing flows.
problem Computing optimal transport maps and Wasserstein barycenters in high-dimensional spaces.
method Uses conditional normalizing flows to approximate distributions and solve the primal problem.
result Shows computational feasibility for hundreds of input distributions and yields accurate results.
Four new methods for computing generalized chi-square distribution.
problem Computing the generalized chi-square distribution accurately and efficiently.
method Two exact and two approximate methods, with software for cdf, pdf, and inverse cdf.
result Comparison of methods' accuracy and speed, identifying best for different cases.
Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are sufficient operations for deep neural networks. We call such models Neural Sampling Machi…
This paper simplifies the Nash Bargaining Solution for use in intellectual property cases.
problem Limited application of Nash Bargaining Solution in assigning intellectual property damages.
method Normalizes the Nash Bargaining Solution and provides a methodology for determining bargaining weight.
result Clarifies the application of Nash Bargaining Solution to specific case facts.
Vanna-Volga is a popular method for the interpolation/extrapolation of volatility smiles. The technique is widely used in the FX markets context, due to its ability to consistently construct the entire Lognormal smile using only three Lognormal market quotes. However, the derivation of the Vanna-Volga method itself is …
New method uses IB to train normalizing flows for better generative classification.
problem Training generative models with information theory for improved classification.
method Developed IB-INNs, a class of conditional normalizing flows trained with IB objective.
result IB-INNs offer improved uncertainty quantification and out-of-distribution detection compared to traditional generative classifiers.
A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary. This ensures eigenvalues with unit norm and thus stable dynamics and training. However …
ButterflyFlow uses butterfly matrices for efficient invertible layers in normalizing flows.
problem Building efficient invertible layers for complex probability distributions.
method Proposes butterfly layers for invertible linear layers, leveraging their ability to capture complex structures.
result ButterflyFlow achieves strong density estimation and significantly better log-likelihoods on various datasets.
Proposes online debiasing estimators for adaptive linear regression.
problem Adaptive data collection leads to non-normal asymptotic behavior in simple methods.
method Online debiasing estimators that correct distributional anomalies.
result Asymptotic normality and minimax lower bound for proposed estimators.
Proposes PER loss to regularize neural network activations to normal distribution.
problem Improving neural network generalization and training speed.
method Regularizes activations to standard normal distribution via projected error function and Wasserstein distance.
result Minimizes Wasserstein distance between activation distribution and standard normal.
This paper puts forth a new formulation and algorithm for the elastic matching problem on unparametrized curves and surfaces. Our approach combines the frameworks of square root normal fields and varifold fidelity metrics into a novel framework, which has several potential advantages over previous works. First, our var…
This paper improves flow models to better handle perturbations in real-world data.
problem Flow models amplify initial errors in perturbed data, leading to poor generalization.
method Utilizes Bernstein-type polynomials to construct Normalizing Flows (NF) for higher robustness.
result Proposed NF framework provides theoretical upper bounds and practical advantages.
Computing partition functions, the normalizing constants of probability distributions, is often hard. Variants of importance sampling give unbiased estimates of a normalizer Z, however, unbiased estimates of the reciprocal 1/Z are harder to obtain. Unbiased estimates of 1/Z allow Markov chain Monte Carlo sampling of "d…
FF algorithm uses goodness as a measure of input quality, derived from likelihood-ratio tests.
problem Training each layer locally with a goodness measure.
method FF algorithm uses a likelihood-ratio test to define goodness, which is the sum of squared activations normalized between layers.
result The goodness measure is a sufficient statistic for a likelihood-ratio test, explaining the FF algorithm's performance.
In low-dimensional topology, many important decision algorithms are based on normal surface enumeration, which is a form of vertex enumeration over a high-dimensional and highly degenerate polytope. Because this enumeration is subject to extra combinatorial constraints, the only practical algorithms to date have been v…
In this paper we present an application of the use of autocopulas for modelling financial time series showing serial dependencies that are not necessarily linear. The approach presented here is semi-parametric in that it is characterized by a non-parametric autocopula and parametric marginals. One advantage of using au…
AlphaGrad optimizes memory usage in RL algorithms by normalizing gradients.
problem Memory overhead and hyperparameter complexity in adaptive optimizers.
method Tensor-wise L2 normalization followed by a smooth hyperbolic tangent transformation controlled by a single parameter.
result AlphaGrad provides enhanced training stability and competitive performance in various RL algorithms.
The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of posterior approximations in order to allow for efficient inference, focusing on mean-field or other simple structured approximations. This restricti…
CIFs improve VI by providing flexible posteriors for complex topologies.
problem Complex posterior distributions in VI problems.
method Using CIFs as part of an auxiliary VI scheme, exploiting conditional independence.
result CIFs yield low-variance estimators of model evidence and improve VI results.
We prove that the marginal densities of a global probability mass function in a primal normal factor graph and the corresponding marginal densities in the dual normal factor graph are related via local mappings. The mapping depends on the Fourier transform of the local factors of the models. Details of the mapping, inc…
Paper proposes robust LAD estimators for 2D sinusoidal model, proving consistency and normality.
problem Estimation of parameters in 2D sinusoidal models with outliers or heavy-tailed noise.
method Least absolute deviation (LAD) estimators for robust parameter estimation.
result Strong consistency and asymptotic normality of LAD estimators for 2D sinusoidal model parameters.
The paper analyzes the randomized midpoint method for Langevin diffusions, revealing biases and asymptotic properties.
problem Analyzing biases and asymptotic properties of the randomized midpoint method for Langevin diffusions.
method Characterization of stationary distribution and asymptotic normality for numerical integration.
result The step-size needs to go to zero for the method to be asymptotically unbiased.
This paper improves bandwidth selectors for SPBNs to enhance their performance.
problem Suboptimal density estimation and reduced predictive performance in SPBNs due to normal rule bandwidth selection.
method Theoretical framework for state-of-the-art bandwidth selectors (cross-validation and plug-in methods) are established and evaluated.
result Cross-validation selectors outperform the normal rule, especially in high sample size scenarios.
This paper uses linear rational splines for invertible modeling, offering a simpler inverse and similar costs.
problem Creating expressive invertible models with tractable Jacobian determinants.
method Replacing affine transformations with linear rational splines in coupling layers.
result Linear rational splines offer a simpler inverse and similar costs for inference and generation.
NVAE improves VAE performance on large image datasets.
problem Improving variational autoencoder performance for large image datasets.
method Deep hierarchical VAE with depth-wise separable convolutions and batch normalization, residual parameterization of Normal distributions, and spectral regularization.
result NVAE achieves state-of-the-art results on MNIST, CIFAR-10, CelebA 64, and CelebA HQ datasets.
TROLL improves RL for LLMs by replacing clipping with a trust region projection.
problem Clipping in RL for LLMs causes instability and suboptimal performance.
method TROLL uses a discrete differentiable trust region projection to replace clipping, balancing computational cost and effectiveness.
result TROLL consistently outperforms PPO-like clipping in training speed, stability, and final success rates.