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.
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.
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.
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 …
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.
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). 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.
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.
A framework is presented for unsupervised learning of representations based on infomax principle for large-scale neural populations. We use an asymptotic approximation to the Shannon's mutual information for a large neural population to demonstrate that a good initial approximation to the global information-theoretic o…
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…
New method learns population dynamics from snapshots using JKO scheme and inverse optimization.
problem Recovering underlying process governing particle evolution from discrete time samples.
method Combines JKO scheme with inverse optimization techniques for end-to-end adversarial training.
result Improved performance over prior JKO-based methods with theoretical guarantees.
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…
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.
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.
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.
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.
Parallel recordings of neural spike counts have revealed the existence of context-dependent noise correlations in neural populations. Theories of population coding have also shown that such correlations can impact the information encoded by neural populations about external stimuli. Although studies have shown that the…
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.
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 has been an emerging tool for various aspects of infectious diseases including tuberculosis surveillance and detection. However, WHO provided no recommendations on using computer-aided tuberculosis detection software because of the small number of studies, methodological limitations, and limited genera…
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.
New approach uses 'growth' and 'harvesting' concepts to improve deep learning models.
problem Current deep learning models lack transparency and high convergence rates.
method Reconsider neural networks as single-species population dynamics with balanced growth and harvesting rates.
result SGD with balanced growth and harvesting rates outperforms adaptive methods in all three requirements.
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.
Low-rank structure emerges in neural networks during learning.
problem Understanding the evolution of synaptic connectivity over learning.
method Investigated the rank of 3-tensor formed by weight matrices throughout learning.
result Inferred weights are low-tensor-rank and evolve in a fixed low-dimensional subspace.
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.
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.
Paper introduces a new method for improving reinforcement learning performance using transfer learning.
problem Improving reinforcement learning performance with limited sample sizes in dynamic decision-making scenarios.
method Developed a novel ``re-weighted targeting procedure'' and ``transfer deep Q∗-learning'' approach. result Demonstrated improved reinforcement learning performance through strategic sample construction.
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 …
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.
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…
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 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.
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.
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…
Automates RL with sample-efficient hyperparameter optimization.
problem Challenges in applying deep RL due to hyperparameter sensitivity and inefficiency.
method Population-based AutoRL framework for meta-optimizing RL algorithms and architectures.
result Reduces the number of environment interactions needed for meta-optimization by up to an order of magnitude.
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.
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…
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.
Method reconstructs neuron models from spike times efficiently.
problem Reconstructing neuron models from spike times in degenerate populations.
method Combining deep learning with DICs to map spike times to DIC densities and generate degenerate CBM populations.
result Fast and scalable reconstruction of degenerate populations from spike recordings.
Study uses machine learning to predict predator-prey dynamics without prior knowledge.
problem Predicting predator-prey interactions without prior knowledge of the system.
method Applied Neural Ordinary Differential Equations (Neural ODEs) and Universal Differential Equations (UDEs) to the Lotka-Volterra model.
result UDEs outperform Neural ODEs in predicting predator-prey dynamics, especially in noisy data.
D2SRM solves complex PDEs using deep learning.
problem High-dimensional, Hessian-dependent fully nonlinear parabolic PDEs.
method Single scalar space-time network generating derivative-consistent approximations trained through residuals and penalties.
result Well-posedness and convergence theory established for globally Lipschitz equations.
Novel graph theory for neural networks improves understanding of their structure and performance.
problem Understanding the structural benefits and generalization power of neural networks.
method Developed a novel graph theoretical formulation and extended error analysis for neural networks.
result Similar a priori estimates can be obtained for neural networks under certain conditions, independent of input dimension.
Recently, over-parameterized neural networks have been extensively analyzed in the literature. However, the previous studies cannot satisfactorily explain why fully trained neural networks are successful in practice. In this paper, we present a new theoretical framework for analyzing over-parameterized neural networks …
Develops robust learning methods for datasets with sub-populations.
problem Robust performance and generalization to unseen testing populations in datasets with sub-populations.
method Min-max-regret (MMR) formulation for distribution-free robust hierarchical model.
result Empirical MMR enjoys regret guarantees on training and unseen testing populations.
Despite rapid advances in machine learning tools, the majority of neural decoding approaches still use traditional methods. Modern machine learning tools, which are versatile and easy to use, have the potential to significantly improve decoding performance. This tutorial describes how to effectively apply these algorit…
Locally learned synaptic failure enables complete Bayesian inference.
problem Bayesian inference in neural networks.
method Biologically constrained neural network with synaptic failure and lateral inhibition.
result Synaptic failure allows sampling from both epistemic and aleatoric distributions.
Proposes a federated transfer learning method to improve precision medicine models for underrepresented populations.
problem Underrepresentation of minorities in precision medicine research leads to underperforming risk prediction models.
method Two-way federated transfer learning strategy integrating diverse populations and healthcare institutions.
result Improves risk prediction models for underrepresented populations, reducing performance gaps.
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…