Adversarial learning of probabilistic models has recently emerged as a promising alternative to maximum likelihood. Implicit models such as generative adversarial networks (GAN) often generate better samples compared to explicit models trained by maximum likelihood. Yet, GANs sidestep the characterization of an explici…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Maximum Likelihood Training”
Maximum likelihood training improves the performance of score-based diffusion models.
problem Training score-based diffusion models with maximum likelihood.
method Trained by minimizing a weighted combination of score matching losses, with a specific weighting scheme that bounds negative log-likelihood.
result Maximum likelihood training improves the log-likelihood of score-based diffusion models across multiple datasets.
Paper proposes efficient training for normalizing flows in Boltzmann generators.
problem Training normalizing flows for Boltzmann generators is computationally challenging and unstable.
method Regression Training of Normalizing Flows (RegFlow) using -regression.
result RegFlow enables efficient and stable training of normalizing flows for Boltzmann generators.
Investigating maximum likelihood based training of infinite mixtures for uncertainty quantificationcs.LG
This work investigates training infinite mixtures with maximum likelihood for improved uncertainty quantification.
problem Improving uncertainty quantification in neural networks.
method Investigates training infinite mixtures with maximum likelihood instead of variational inference.
result The proposed method leads to stochastic networks with increased predictive variance, improved robustness, and higher entropy on out-of-distribution data.
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.
A new method improves text generation quality and diversity.
problem Exposure bias in Maximum Likelihood Estimation for text generation.
method ψ-MLE, a new training scheme based on density ratio estimation.
result ψ-MLE outperforms Maximum Likelihood Estimation and other models in text generation quality and diversity.
EBMs trained with ML are shown to behave like GANs with a self-adversarial loss.
problem Training EBMs with ML is intractable due to intractable unnormalized distributions.
method Replaced MCMC with deterministic gradient descent ODE solutions to study density induced by dynamics.
result EBM training is effectively a self-adversarial procedure rather than ML estimation.
Maximum likelihood estimation fails to be well-posed in Gaussian process regression.
problem Establishing well-posedness of maximum likelihood estimation in Gaussian process regression.
method Analyzing the conditions under which maximum likelihood estimation is not Lipschitz in the data with respect to the Hellinger distance.
result Maximum likelihood estimation is not well-posed in the noiseless data setting for any Gaussian process with a stationary covariance function whose lengthscale parameter is estimated using maximum likelihood.
We propose a robust estimator to improve maximum likelihood in probabilistic models.
problem Overfitting and sensitivity to noise in maximum likelihood estimation.
method Distributionally robust maximum likelihood estimator that minimizes worst-case expected log-loss.
result The robust estimator is statistically consistent and performs well in regression and classification tasks.
Connectionist temporal classification (CTC) is widely used for maximum likelihood learning in end-to-end speech recognition models. However, there is usually a disparity between the negative maximum likelihood and the performance metric used in speech recognition, e.g., word error rate (WER). This results in a mismatch…
Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matchingstat.ML
This work improves likelihood of score-based diffusion ODEs using high-order denoising score matching.
problem The gap between maximum likelihood and score matching objectives for score-based diffusion ODEs.
method High-order denoising score matching to maximize likelihood.
result Score-based diffusion ODEs achieve better likelihood on synthetic and CIFAR-10 data.
Generative Adversarial Networks (GANs) enjoy great success at image generation, but have proven difficult to train in the domain of natural language. Challenges with gradient estimation, optimization instability, and mode collapse have lead practitioners to resort to maximum likelihood pre-training, followed by small a…
New method improves neural spike train models by minimizing divergence directly, leading to better performance.
problem Poor performance and divergence issues in spike train models using maximum likelihood estimation.
method Directly minimize maximum mean discrepancy using spike train kernels and stochastic optimization.
result The proposed method generates well-behaved models with better control over feature trade-offs.
A new method optimizes neural sequence models for better task performance.
problem Training neural sequence models with maximum likelihood estimation ignores task losses.
method Maximum likelihood guided parameter search (MGS) in the parameter space.
result MGS optimizes sequence-level losses, reducing repetition and non-termination.
Paper proposes energy objective for training normalizing flows without determinants.
problem Challenges in training normalizing flows due to Jacobian determinants.
method Introduces energy objective based on proper scoring rules, determinant-free.
result Energy objective supports novel model families and competitive performance.
Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks, alternative non-likelihood training criteria have been proposed. Whilst not necessarily…
Innovative game theory approach optimizes survival analysis metrics.
problem Survival analysis models trained with maximum likelihood do not directly optimize criteria like Brier score or Bernoulli log likelihood.
method Inverse-Weighted Survival Games: Construct objectives from re-weighted estimates featuring the other model, holding the latter fixed during training.
result Games optimize Brier score on simulations and real-world data.
We consider the problem of training probabilistic conditional random fields (CRFs) in the context of a task where performance is measured using a specific loss function. While maximum likelihood is the most common approach to training CRFs, it ignores the inherent structure of the task's loss function. We describe alte…
New particle algorithms optimize latent variable models.
problem Optimizing latent variable models for maximum likelihood estimation.
method Identify gradient flows associated with free energy functional and discretize them to create particle-based algorithms.
result Novel particle algorithms scale to high-dimensional settings and perform well in experiments.
A new method normalizes EBM training by introducing a learnable parameter.
problem Training energy-based models with maximum likelihood is challenging due to intractable normalisation constants.
method Proposes a self-normalised log-likelihood (SNL) objective that introduces a learnable parameter representing the normalisation constant.
result The SNL objective is a lower bound of the log-likelihood and can be directly optimised using stochastic gradient techniques.
Label shift refers to the phenomenon where the prior class probability p(y) changes between the training and test distributions, while the conditional probability p(x|y) stays fixed. Label shift arises in settings like medical diagnosis, where a classifier trained to predict disease given symptoms must be adapted to sc…
Transformer learns to estimate negative binomial parameters efficiently.
problem Parameter estimation for over-dispersed count data in large screens.
method Pre-trained transformer trained on synthetic data generation to invert parameter to count transformation.
result Method of moments provides faster, more efficient, and better-calibrated estimates.
CMLE reduces spurious correlations in deep models.
problem Spurious correlations in deep learning models.
method Counterfactual Maximum Likelihood Estimation (CMLE) on interventional distribution.
result CMLE outperforms regular MLE in out-of-domain generalization and spurious correlation reduction.
Paper proposes a method to estimate true positive proportion without knowing it.
problem Bias in binary classifier performance due to different positive item proportions.
method Maximum likelihood estimator for true proportion of positives.
result Method accurately estimates true positive proportion in data sets.
To combine explicit and implicit generative models, we introduce semi-implicit generator (SIG) as a flexible hierarchical model that can be trained in the maximum likelihood framework. Both theoretically and experimentally, we demonstrate that SIG can generate high quality samples especially when dealing with multi-mod…
A new path gradient estimator speeds up normalizing flows without sacrificing accuracy.
problem High computational cost and limited scalability of path gradient estimators for normalizing flows.
method Proposed a fast path gradient estimator that improves computational efficiency and scalability.
result The new estimator achieves superior performance and reduced variance across various applications.
Unified ML and adversarial learning via α-divergence.
problem Combining strengths of ML and adversarial learning for better generative models.
method Proposes an α-Bridge to unify ML and adversarial learning using α-divergence.
result Generalizations of the α-Bridge are related to recent adversarial learning regularization approaches.
Dual training method for EBMs with overparametrized neural networks.
problem Training EBMs with non-convex energies is challenging.
method Derive variational principles and dual GDA algorithm for feature-learning regime.
result Dual GDA algorithm performs best with similar time scales for features and particles.
Improved autoregressive models generate higher quality images and are more robust to noise.
problem Generating high-quality images from autoregressive models.
method Noise conditional maximum likelihood estimation (MLE) with score-based sampling.
result Models trained with noise conditional MLE achieve better test likelihoods and generate higher quality images.
Deterministic training improves generative autoencoder performance.
problem Stochastic training limits generative autoencoder performance.
method Invertible layers for deterministic training.
result AEFs outperform VAEs in log-likelihood and sample quality.
A new layer, funnel, reduces dimensionality in flows for better performance.
problem Training high-dimensional models efficiently and accurately.
method Constructing dimension-reducing surjective flows using the funnel layer.
result The funnel layer improves model performance with a smaller latent space.
Efficiently estimates GEV distribution parameters using neural networks.
problem Computational intensity of maximum likelihood estimation for GEV distribution.
method Neural network-based likelihood-free estimation method.
result Comparable accuracy to maximum likelihood method with significant speedup.
This paper proposes a new RV prediction model using neural distributional transformation and co-training.
problem Predicting skewed and fat-tailed realized volatility (RV) is challenging.
method The paper uses a neural distributional transformation and co-training to predict RV. It jointly trains the transformation and prediction model using a maximum-likelihood objective function.
result The proposed method significantly outperforms other methods on a dataset of 100 stocks.
Proposes a new method for high-dimensional density estimation.
problem Estimating high-dimensional probability density functions efficiently.
method Tensorizing flow method combining tensor-train and flow-based generative modeling.
result Efficiently constructs an approximate density in tensor-train form and trains a flow model to match empirical distribution.
Restricted Boltzmann Machines (RBM) have attracted a lot of attention of late, as one the principle building blocks of deep networks. Training RBMs remains problematic however, because of the intractibility of their partition function. The maximum likelihood gradient requires a very robust sampler which can accurately …
Unbiased gradient estimation improves VAE performance.
problem Training VAEs via maximum likelihood is difficult due to intractable integrals.
method Introduced unbiased estimators of the log-likelihood gradient using coupled Markov chains.
result Unbiased estimators lead to better predictive performance in VAEs.
This paper explores adversarial robustness of flow-based generative models.
problem Robustness of flow-based generative models to adversarial attacks.
method Theoretical and empirical analysis of adversarial robustness for simple and complex flow-based models.
result Flow-based generative models are highly sensitive to adversarial attacks, but robustness can be significantly improved using hybrid adversarial training.
New analysis shows entropy term cancels out in likelihood-based OOD detection.
problem Curious likelihood values for out-of-distribution data.
method Decomposed average likelihood into KL divergence and entropy terms.
result Entropy term explains OOD behaviour and cancels out in expectation.
Stochastic Normalizing Flowsstat.ML
Stochastic normalizing flows use SDEs for efficient training and sampling.
problem Efficient maximum likelihood estimation and variational inference.
method Continuous normalizing flows extended with stochastic differential equations (SDEs) and rough path theory.
result Stochastic normalizing flows enable efficient training and sampling from complex distributions.
Deep models memorize training data in geophysical inversion, leading to biased posterior distributions.
problem Memorization of training data biases learned priors in geophysical inverse problems.
method Casting generative models' training as maximum likelihood, we show memorization results in a reweighted empirical distribution for diffusion models, leading to Gaussian mixture priors and posteriors.
result Memorization leads to posterior distributions that are likelihood-weighted lookup among stored training examples, affecting full waveform inversion outcomes.
Modern applications and progress in deep learning research have created renewed interest for generative models of text and of images. However, even today it is unclear what objective functions one should use to train and evaluate these models. In this paper we present two contributions. Firstly, we present a critique o…
This paper proposes a method to train energy-based models using variational auto-encoders for efficient sampling.
problem Training energy-based models by maximum likelihood is challenging due to intractable partition functions and difficult sampling from the model distribution.
method The authors propose using a variational auto-encoder to initialize finite-step MCMC sampling, specifically Langevin dynamics, to train the energy-based model.
result The proposed method enables training energy-based models using maximum likelihood, generating samples comparable to GANs and EBMs.
Score matching efficiency tied to distribution isoperimetric properties.
problem Understanding when score matching is as efficient as maximum likelihood.
method Connecting score matching efficiency to isoperimetric constants of distributions.
result Score matching is statistically efficient when the distribution has a small isoperimetric constant.
We present an asymptotic analysis of Viterbi Training (VT) and contrast it with a more conventional Maximum Likelihood (ML) approach to parameter estimation in Hidden Markov Models. While ML estimator works by (locally) maximizing the likelihood of the observed data, VT seeks to maximize the probability of the most lik…
Reduces quantifier variance with accuracy optimization of base classifier.
problem Minimizing quantifier variance under prior probability shift.
method Optimizes the Brier score of a base classifier for training data.
result Optimizing Brier score on training data reduces quantifier variance on test data.
Supervised topic models utilize document's side information for discovering predictive low dimensional representations of documents. Existing models apply the likelihood-based estimation. In this paper, we present a general framework of max-margin supervised topic models for both continuous and categorical response var…
Thermodynamic Machine Learning through Maximum Work Productioncond-mat.stat-mech
Work maximization guides machine learning models in adaptive systems.
problem How machine learning models can be optimized for thermodynamic efficiency.
method Introducing thermodynamic principle to compare with maximum-likelihood principle.
result Maximum-work models are equivalent to maximum-likelihood models in adaptive systems.
New method trains energy-based models faster and more stably.
problem Training efficiency and stability of energy-based models.
method EBFlow with score-matching objectives.
result EBFlow achieves significant speedup and better performance.