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

2595197781,037 · Jun 202019922001200920172026
48 results for conditional training

Adaptive networks improve model robustness through conditional normalization.

problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.

TR0N turns pre-trained models into conditional ones with minimal training.

problem Creating conditional models from pre-trained unconditional models.
method Lightweight stochastic mapping between conditions and latent space, improved through Langevin dynamics.
result Achieves zero-shot FID of 10.9 on MS-COCO, outperforming alternatives.

Machine-learned diagnosis models have shown promise as medical aides but are trained under a closed-set assumption, i.e. that models will only encounter conditions on which they have been trained. However, it is practically infeasible to obtain sufficient training data for every human condition, and once deployed such …

2019-10-07abs ↗pdf ↗

We introduce a new framework for training deep generative models for high-dimensional conditional density estimation. The Bottleneck Conditional Density Estimator (BCDE) is a variant of the conditional variational autoencoder (CVAE) that employs layer(s) of stochastic variables as the bottleneck between the input xx a…

2016-11-25abs ↗pdf ↗

Framework transfers complementary operating conditions to train anomaly detectors.

problem Training anomaly detectors on changing operating conditions requires comprehensive data, which is hard to obtain.
method Proposes unsupervised transfer learning to align and combine data from different units.
result Demonstrates improved anomaly detection in changing operating conditions.

Paper explores challenges in training PINNs and loss landscape effects.

problem Challenges in training Physics-Informed Neural Networks (PINNs) due to loss landscape issues.
method Examined gradient-based optimizers Adam, L-BFGS, and their combination Adam+L-BFGS, and introduced NysNewton-CG (NNCG).
result Adam+L-BFGS outperforms other optimizers, and NysNewton-CG significantly improves PINN performance.

New analysis reveals batch size effects on stochastic conditional gradient methods.

problem Understanding the role of batch size in stochastic conditional gradient methods.
method Deriving a new analysis focusing on momentum-based stochastic conditional gradient algorithms (e.g., Scion).
result Increasing batch size initially improves optimization accuracy but can degrade performance beyond a critical threshold.

New insights into how linear classifiers and leaky ReLU networks can overfit without harming generalization.

problem Understanding conditions for benign overfitting in linear classifiers and leaky ReLU networks.
method Utilizing Karush--Kuhn--Tucker (KKT) conditions for margin maximization.
result Satisfaction of KKT conditions leads to benign overfitting in linear classifiers and leaky ReLU networks.

Training-free model learns SDE dynamics without training, accelerating parameter studies.

problem High computational cost of simulating parameter-dependent SDEs.
method Training-free conditional diffusion model with joint kernel-weighted Monte Carlo estimator.
result Accurate approximation of conditional distributions across varying parameter values.

This paper analyzes deep and wide transformer training dynamics.

problem Understanding the training dynamics of infinitely deep and wide transformers.
method Develops a mean-field framework for gradient-based training of transformers, controlling a neural PDE.
result Establishes a rigorous foundation for gradient-based transformer training, proving convergence to global minima.

Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for representing class-specific information using conditional Batch Normalization (cBN). In this paper we pro…

2018-06-01abs ↗pdf ↗

New bounds on neural network test loss derived from conditional information measures.

problem Estimating test loss of neural networks trained on limited data.
method Framework based on conditional information density between hypothesis and training set.
result Tail bounds on test loss decay as 1/n, improving over previous 1/sqrt{n} bounds.

Neural Networks are being integrated into safety critical systems, e.g., perception systems for autonomous vehicles, which require trained networks to perform safely in novel scenarios. It is challenging to verify neural networks because their decisions are not explainable, they cannot be exhaustively tested, and finit…

2019-12-20abs ↗pdf ↗

The paper distinguishes between conditional and marginal processes in language models and discusses conditions for usefulness.

problem The conditional nature of language models trained on observed sequences and the need for marginal text-only processes.
method Distinguishing between full conditional language process, marginal text-only process, and model-induced distribution; analyzing assumptions of stationarity and ergodicity.
result The marginal text-only law is useful only when the observed prefix is an approximately sufficient statistic for the latent circumstances relevant to continuation.

Deep learning methods are becoming widely used for restoration of defects associated with fluorescence microscopy imaging. One of the major challenges in application of such methods is the availability of training data. In this work, we propose a unified method for reconstruction of multi-defect fluorescence microscopy…

2019-10-31abs ↗pdf ↗

New method improves training-free guidance for diffusion models, achieving state-of-the-art results.

problem Accurate, training-free guidance for conditional generation in diffusion models.
method Sequential Monte Carlo (SMC) framework with Multi-Level Monte Carlo (MLMC) variance reduction.
result Achieves state-of-the-art results on CIFAR-10 and ImageNet datasets with significant cost reduction.

The paper derives uniform stability-based coverage bounds for conformal prediction methods.

problem Establishing theoretical guarantees for conformal prediction methods.
method Uniform stability perspective applied to full-conformal, jackknife+, and CV+ prediction regions.
result Coverage bounds for finite-dimensional models derived using a concentration argument.

We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector XX. The NC is a function NC(xa,a,r)NC(x \cdot a, a, r) that leverages adversarial training to match each conditional distribution P(XrXa=xa)P(X_r|X_a=x_a). After training, the NC generalizes to …

2019-02-22abs ↗pdf ↗

New method uses generative models to estimate aleatoric uncertainty without strict data restrictions.

problem Estimating aleatoric uncertainty with limited data distribution or dimensionality.
method Conditional generative models and two metrics for measuring distributional discrepancies.
result Metrics accurately measure conditional distributional discrepancies and train competitive models.

Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called Generative Matching Network which is inspired by the recently proposed matching networks …

2016-12-07abs ↗pdf ↗

Training data-driven approaches for complex industrial system health monitoring is challenging. When data on faulty conditions are rare or not available, the training has to be performed in a unsupervised manner. In addition, when the observation period, used for training, is kept short, to be able to monitor the syste…

2019-07-15abs ↗pdf ↗

Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to condition on to both the generator and discriminator. We show that this…

2014-11-06abs ↗pdf ↗

Algorithm optimizes biological sequences using bootstrapped training with a score-conditioned generator.

problem Optimizing biological sequences for a black-box score function.
method Bootstrapped training of score-conditioned generator (BootGen) algorithm.
result Our method outperforms competitive baselines on biological sequential design tasks.

A novel framework uses goal-conditioned reinforcement learning to generate diverse samples.

problem Generating high-quality, diverse samples from generative models.
method Two agents: GC-agent learns to reconstruct the training set, S-agent learns to imitate GC-agent without knowing the goals.
result Empirically, the method generates diverse and high-quality samples in image synthesis.

The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions. In this work, we propose an adversarial speaker verification (ASV) scheme to lear…

2019-04-29abs ↗pdf ↗

Transformers learn a mesa-optimizer to implement in-context learning.

problem Understanding the convergence of autoregressive training to a mesa-optimizer.
method Investigated a one-layer linear causal self-attention model autoregressively trained by gradient flow.
result Proved that autoregressive training converges to a gradient descent step for an OLS problem, validating the mesa-optimizer hypothesis.

A RL-based method adds conditional controls to pre-trained diffusion models.

problem Precise control over generated samples in diffusion models.
method Formulates the task as an RL problem, using a classifier and KL divergence as reward functions.
result Produces soft-optimal policies that maximize reward functions, enabling conditional sampling.

Optimal gradient quantization reduces communication costs in distributed deep learning.

problem High communication costs in distributed training of deep neural networks.
method Deduced optimal gradient quantization conditions for binary and multi-level quantization, developed novel schemes for dynamic quantization levels.
result Demonstrated superior performance of proposed quantization schemes on CIFAR and ImageNet datasets.

A method for estimating signal distributions from inverse problems using normalizing flows.

problem Estimating the distribution of the underlying signal from observations in inverse problems.
method A framework for approximate inference on a pre-trained unconditional flow model, using a composition of two flow models for stable variational inference.
result Our method produces high-quality samples with uncertainty quantification and can be amortized for zero-shot inference.

Modelling statistical relationships beyond the conditional mean is crucial in many settings. Conditional density estimation (CDE) aims to learn the full conditional probability density from data. Though highly expressive, neural network based CDE models can suffer from severe over-fitting when trained with the maximum …

2019-07-21abs ↗pdf ↗

AugMask trains diffusion models on incomplete tabular data by augmenting missing values and applying denoising supervision.

problem Training diffusion models on incomplete tabular data with missing values.
method AugMask uses stochastic augmentation and denoising supervision to adapt diffusion models to incomplete data.
result AugMask enables diffusion-based tabular generators to outperform specialized missing-aware baselines across various datasets and missingness regimes.