Paper uses neural networks to calibrate Lee-Carter models for multiple populations.
problem Calibrating Lee-Carter models for multiple populations with neural networks.
method Developed neural network architectures to fit Lee-Carter and Poisson Lee-Carter models simultaneously.
result Smooth and less sensitive parameter estimates, improved forecasting performance.
Active learning method for neural population dynamics using optogenetics.
problem Efficiently selecting neurons to stimulate for identifying neural population dynamics.
method Developed active learning procedure for low-rank regression to determine informative photostimulation patterns.
result Demonstrated a two-fold reduction in data required for predictive power using low-rank linear dynamical systems model.
NPE trains neural networks to approximate posterior distributions in SIR models from final outcome data.
problem Computational challenges in Bayesian inference for SIR models with final outcome data.
method Neural posterior estimation (NPE) using a logNormal posterior approximated by a neural network.
result NPE accurately recovers reference posteriors across various population sizes and transmission regimes.
A powerful approach for understanding neural population dynamics is to extract low-dimensional trajectories from population recordings using dimensionality reduction methods. Current approaches for dimensionality reduction on neural data are limited to single population recordings, and can not identify dynamics embedde…
Mesoscopic model infers neural population dynamics from spike trains.
problem Challenges in fitting mechanistic spiking networks to empirical population data.
method Fit mesoscopic model to aggregate population activity, using likelihood of single-neuron and connectivity parameters.
result Extracts posterior correlations between model parameters and defines subsets of parameters able to reproduce data.
Improved neural population modeling using shared features and ensemble detection.
problem Missing shared coding properties in neural latent variable models.
method Feature sharing across tuning curves and soft clustering of neurons.
result More interpretable and better-performing neural population models.
Model captures context-dependent neural correlations using Poisson mixtures.
problem Capturing context-dependent noise correlations in neural populations.
method Conditional finite mixtures of Poisson distributions, cross-validation for dimensionality, EM algorithm.
result Model successfully captures stimulus-dependent correlations in V1 neuron responses.
Neural networks model COVID-19 spread with partial isolation data.
problem Modeling the spread of COVID-19 with limited data.
method Semi-supervised neural networks solving inverse problems.
result Estimates optimal conditions for virus spread and passive population.
Aims to describe neural network training dynamics using two-time-scale models.
problem Lack of a general mathematical description of neural network training.
method Introduces a theoretical framework based on two-time-scale population dynamics.
result Derives selection-mutation equations and effective fitness for hyperparameters.
NeuPL learns diverse policies in strategy games efficiently.
problem Iterative training of policies in strategy games leads to under-trained good-responses and wasteful repetition.
method NeuPL uses a single conditional model to represent a population of policies, offering convergence guarantees and transfer learning.
result NeuPL achieves better performance and efficiency across various domains, enabling access to novel strategies.
Accurate statistical models of neural spike responses can characterize the information carried by neural populations. But the limited samples of spike counts during recording usually result in model overfitting. Besides, current models assume spike counts to be Poisson-distributed, which ignores the fact that many neur…
Neural population activity often exhibits rich variability and temporal structure. This variability is thought to arise from single-neuron stochasticity, neural dynamics on short time-scales, as well as from modulations of neural firing properties on long time-scales, often referred to as "non-stationarity". To better …
APG samplers use neural suff stats to improve deep model inference.
problem Efficient inference in deep generative models.
method Amortized population Gibbs, neural suff stats, KL divergence minimization.
result Significant improvement in inference accuracy.
Deep Random Splines model neural activity data with better dimensionality.
problem Modeling neural population data with shape constraints.
method Deep neural network transforming Gaussian noise into spline parameters.
result Better dimensionality reduction of neural spiking activity.
Neurons in higher cortical areas, such as the prefrontal cortex, are known to be tuned to a variety of sensory and motor variables. The resulting diversity of neural tuning often obscures the represented information. Here we introduce a novel dimensionality reduction technique, demixed principal component analysis (dPC…
An explosion of high-throughput DNA sequencing in the past decade has led to a surge of interest in population-scale inference with whole-genome data. Recent work in population genetics has centered on designing inference methods for relatively simple model classes, and few scalable general-purpose inference techniques…
Gradient descent struggles with high-dimensional data fitting.
problem Gradient descent struggles with high-dimensional data fitting.
method Gradient descent training of a two-layer neural network on empirical or population risk.
result Gradient descent training may not decrease population risk faster than t−4/(d−2) under mean field scaling. RECaST calibrates source models for target populations with uncertainty quantification.
problem Uncertainty in transfer learning predictions.
method Random effect calibration of source to target models.
result Nominal coverage of prediction sets in linear models, robust to nonlinear approximations.
Bubblewrap predicts neural dynamics online, scaling to thousands of neurons.
problem Direct testing of neural population hypotheses requires online inference of neural state.
method Soft tiling of neural manifold with fast, stable dimensionality reduction.
result Bubblewrap model outperforms existing methods in noisy conditions.
New method tests CMI using deep neural networks for high-dimensional data.
problem Testing conditional mean independence in high-dimensional settings.
method Population CMI measure and bootstrap-based testing with deep generative neural networks.
result Strong empirical performance and versatility in various scenarios.
New method improves NN performance across various settings.
problem Improving neural network performance across different datasets and architectures.
method Population Gradients (PG) method to calculate non-local gradient estimates.
result Significantly improves final performance across architectures, data-sets, and hyper-parameters.
Paper develops NN models for diabetes screening using NHANES data.
problem Developing accurate predictive models for diabetes in diverse populations.
method Proposes a neural network framework with survey weights, uncertainty quantification.
result Robust risk score models for diabetes in US population.
When governed by underlying low-dimensional dynamics, the interdependence of simultaneously recorded population of neurons can be explained by a small number of shared factors, or a low-dimensional trajectory. Recovering these latent trajectories, particularly from single-trial population recordings, may help us unders…
MutaGAN predicts mutations of evolving protein populations using GANs.
problem Predicting mutations in evolving protein populations.
method Generative adversarial networks (GANs) with recurrent neural networks (RNNs).
result MutaGAN generates complete protein sequences with mutations.
FIRE PBT improves neural network training by focusing on long-term performance.
problem Greedy decision mechanisms in PBT lead to poor long-term performance.
method FIRE PBT uses a fitness metric to encourage long-term performance over short-term improvements.
result FIRE PBT outperforms PBT on ImageNet and matches hand-tuned learning rates.
Proposes a neural network method to combine nonprobability and probability survey samples.
problem Combining nonprobability and probability survey samples for accurate population mean estimation.
method Uses a deep neural network to estimate sampling scores from nonprobability samples and combines them with probability sample information.
result Proposed estimators improve robustness to parametric propensity-score misspecification, especially for nonlinear selection mechanisms.
dLDS models neural dynamics as sparse combinations of simpler components.
problem Understanding complex neural dynamics at a population level.
method Proposes a decomposed dynamical system model trained through dictionary learning.
result Model efficiently captures and demix diverse neural dynamics.
Study shows neural networks outperform traditional methods in speaker identification.
problem Open-set speaker identification with large populations.
method Discriminative neural networks compared to Gaussian mixture models.
result Multi-class neural networks outperform traditional methods for large speaker populations.
ENN method uses expectile regression for genetic data analysis of complex diseases.
problem Discover additional genetic variants contributing to complex diseases.
method Developed an expectile neural network (ENN) method integrating expectile regression and neural networks.
result ENN method outperforms existing expectile regression in discovering genetic variants predisposing to sub-populations.
We extend manifold capacity to nonlinear neural representations with contextual information.
problem Efficient processing of information through neural representations.
method Theoretical framework leveraging latent directions in input space related to contextual information.
result Derivation of an exact formula for context-dependent manifold capacity.
Scaffolding sets improve predictor correctness across subsets.
problem Ensuring predictor correctness across multiple subsets.
method Inspired by neural nets, constructing scaffolding sets to ensure correctness.
result Scaffolding sets ensure predictor correctness, not just calibration.
Gradient descent learns over-param neural nets better than NTK.
problem Learning over-parametrized neural networks with ReLU activations.
method Gradient descent from random initialization on a Gaussian input distribution.
result Gradient descent achieves population loss o(1/d), while NTK achieves Ω(1/d). Optimizes weights for better model performance in shifting data.
problem Improper importance weighting leads to poor model performance in data shifts.
method Interprets weights as a bias-variance trade-off and optimizes them simultaneously with model parameters.
result Optimizing weights significantly improves model generalization performance.
The paper addresses differentially private learning for neural networks, focusing on risk bounds and algorithm feasibility.
problem Achieving differentially private learning for neural networks with theoretical guarantees.
method Developed algorithms and theoretical analysis for differentially private stochastic optimization of neural networks.
result Established theoretical bounds for excess population risk in differentially private learning of neural networks.
BayesFlow learns complex models using neural networks.
problem Estimating parameters in complex, non-likelihood models.
method Invertible neural networks for global Bayesian inference.
result Global probabilistic mapping from data to parameters.
Study on random matrices in deep neural networks using Gaussian data.
problem Distribution of singular values in product of random matrices in deep learning.
method Free probability theory combined with standard techniques of random matrix theory.
result Justification for applying free probability theory to non-independent random data matrices.
Integrates neural encoders into GLMMs for multimodal data analysis.
problem Scalable Bayesian inference for GLMMs assumes low-dimensional tabular predictors and does not handle high-dimensional modalities.
method Jointly learns modality-specific neural encoders with GLMM objective, performs variance-corrected stochastic-gradient MCMC.
result Preserves interpretable fixed and random effects while scaling to large longitudinal datasets.
This paper studies the landscape of empirical risk of deep neural networks by theoretically analyzing its convergence behavior to the population risk as well as its stationary points and properties. For an l-layer linear neural network, we prove its empirical risk uniformly converges to its population risk at the rat…
A body of recent work in modeling neural activity focuses on recovering low-dimensional latent features that capture the statistical structure of large-scale neural populations. Most such approaches have focused on linear generative models, where inference is computationally tractable. Here, we propose fLDS, a general …
The curse of dimensionality affects neural network optimization, especially with smooth functions.
problem The curse of dimensionality in neural network optimization.
method Examined through the evolution of the parameter distribution under 2-Wasserstein gradient flow.
result The curse of dimensionality persists in neural network optimization, even with smooth functions.
We propose a population-based Evolutionary Stochastic Gradient Descent (ESGD) framework for optimizing deep neural networks. ESGD combines SGD and gradient-free evolutionary algorithms as complementary algorithms in one framework in which the optimization alternates between the SGD step and evolution step to improve th…
Continuous-time SGD converges under certain conditions, useful for deep learning.
problem Minimizing population expected loss in learning problems.
method Continuous-time approximation of stochastic gradient descent.
result Establishes sufficient conditions for convergence, applicable to overparametrized neural networks.
MFM integrates multiple evolving populations using Wasserstein manifold flows.
problem Learning dynamics of multiple interacting populations evolving over time.
method Meta Flow Matching (MFM) integrates vector fields on Wasserstein manifold using amortized flow models and GNN embeddings.
result MFM improves prediction of individual treatment responses on multi-patient single-cell drug screen data.
Simulation-based inference speeds up gravitational wave data analysis.
problem High-dimensional parameter spaces and complex noise in gravitational wave data.
method Simulation-based inference methods using machine learning techniques.
result Simulation-based inference methods improve speed over traditional methods.
Improves Gaussian process factor models for multi-population recordings.
problem Cubic runtime scaling with trial length and group number limits application to large-scale recordings.
method Two approximate approaches: inducing variables and frequency domain.
result Achieved orders of magnitude speed-up with minimal statistical performance impact.
A new model improves analysis of neural activity from calcium imaging.
problem Statistical modeling of deconvolved calcium signals for neural activity interpretation.
method Proposed a zero-inflated gamma (ZIG) model to characterize calcium responses as a mixture of a gamma distribution and a point mass.
result The ZIG model outperforms simpler models in neural encoding and decoding problems.
In order to interact intelligently with objects in the world, animals must first transform neural population responses into estimates of the dynamic, unknown stimuli which caused them. The Bayesian solution to this problem is known as a Bayes filter, which applies Bayes' rule to combine population responses with the pr…
Machine learning helps infer dark matter substructure from strong lensing images.
problem Extracting information about dark matter substructure from strong lensing images is challenging.
method Simulation-based inference techniques and neural networks trained on simulator data.
result Efficiently trained neural networks can estimate likelihood ratios for substructure parameters.