Advances in neural information processing systems最新文献_第3页

Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models. 稀有事件数据和稀疏模型的尺度不变最优抽样。

Advances in neural information processing systems Pub Date : 2024-01-01

Jing Wang, HaiYing Wang, Hao Helen Zhang

{"title":"Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models.","authors":"Jing Wang, HaiYing Wang, Hao Helen Zhang","doi":"","DOIUrl":"","url":null,"abstract":"Subsampling is effective in tackling computational challenges for massive data with rare events. Overly aggressive subsampling may adversely affect estimation efficiency, and optimal subsampling is essential to mitigate the information loss. However, existing optimal subsampling probabilities depends on data scales, and some scaling transformations may result in inefficient subsamples. This problem is more significant when there are inactive features, because their influence on the subsampling probabilities can be arbitrarily magnified by inappropriate scaling transformations. We tackle this challenge and introduce a scale-invariant optimal subsampling function in the context of sparse models, where inactive features are commonly assumed. Instead of focusing on estimating model parameters, we define an optimal subsampling function to minimize the prediction error, using adaptive lasso as an example to outline the estimation procedure and study its theoretical guarantee. We first introduce the adaptive lasso estimator for rare-events data and establish its oracle properties, thereby validating the use of subsampling. Then we derive a scale-invariant optimal subsampling function that minimizes the prediction error of the inverse probability weighted (IPW) adaptive lasso. Finally, we present an estimator based on the maximum sampled conditional likelihood (MSCL) to further improve the estimation efficiency. We conduct numerical experiments using both simulated and real-world data sets to demonstrate the performance of the proposed methods.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"98384-98418"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12245189/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144610442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Robust Mixed-Effects Bandit Algorithm for Assessing Mobile Health Interventions. 一种用于评估移动医疗干预的鲁棒混合效应Bandit算法。

Advances in neural information processing systems Pub Date : 2024-01-01

Easton K Huch, Jieru Shi, Madeline R Abbott, Jessica R Golbus, Alexander Moreno, Walter H Dempsey

引用次数: 0

On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models. 神经网络作为无限树结构概率图模型。

Advances in neural information processing systems Pub Date : 2024-01-01

Boyao Li, Alexander J Thomson, Houssam Nassif, Matthew M Engelhard, David Page

引用次数: 0

Ultrafast classical phylogenetic method beats large protein language models on variant effect prediction. 超快速经典系统发育方法在变异效应预测上优于大型蛋白质语言模型。

Advances in neural information processing systems Pub Date : 2024-01-01

Sebastian Prillo, Wilson Wu, Yun S Song

{"title":"Ultrafast classical phylogenetic method beats large protein language models on variant effect prediction.","authors":"Sebastian Prillo, Wilson Wu, Yun S Song","doi":"","DOIUrl":"","url":null,"abstract":"Amino acid substitution rate matrices are fundamental to statistical phylogenetics and evolutionary biology. Estimating them typically requires reconstructed trees for massive amounts of aligned proteins, which poses a major computational bottleneck. In this paper, we develop a near-linear time method to estimate these rate matrices from multiple sequence alignments (MSAs) alone, thereby speeding up computation by orders of magnitude. Our method relies on a near-linear time cherry reconstruction algorithm which we call FastCherries and it can be easily applied to MSAs with millions of sequences. On both simulated and real data, we demonstrate the speed and accuracy of our method as applied to the classical model of protein evolution. By leveraging the unprecedented scalability of our method, we develop a new, rich phylogenetic model called SiteRM, which can estimate a general site-specific rate matrix for each column of an MSA. Remarkably, in variant effect prediction for both clinical and deep mutational scanning data in ProteinGym, we show that despite being an independent-sites model, our SiteRM model outperforms large protein language models that learn complex residue-residue interactions between different sites. We attribute our increased performance to conceptual advances in our probabilistic treatment of evolutionary data and our ability to handle extremely large MSAs. We anticipate that our work will have a lasting impact across both statistical phylogenetics and computational variant effect prediction. FastCherries and SiteRM are implemented in the CherryML package https://github.com/songlab-cal/CherryML.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"130265-130290"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12143485/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144251069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Text to Blind Motion. 文本到盲动。

Advances in neural information processing systems Pub Date : 2024-01-01

Hee Jae Kim, Kathakoli Sengupta, Masaki Kuribayashi, Hernisa Kacorri, Eshed Ohn-Bar

{"title":"Text to Blind Motion.","authors":"Hee Jae Kim, Kathakoli Sengupta, Masaki Kuribayashi, Hernisa Kacorri, Eshed Ohn-Bar","doi":"","DOIUrl":"","url":null,"abstract":"People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection, blind individuals may have different patterns of movement, such as veering more from a straight path or using touch-based exploration around curbs and obstacles. These behaviors may appear less predictable to motion models embedded in technologies such as autonomous vehicles. Yet, the ability of 3D motion models to capture such behavior has not been previously studied, as existing datasets for 3D human motion currently lack diversity and are biased toward people who are sighted. In this work, we introduce BlindWays, the first multimodal motion benchmark for pedestrians who are blind. We collect 3D motion data using wearable sensors with 11 blind participants navigating eight different routes in a real-world urban setting. Additionally, we provide rich textual descriptions that capture the distinctive movement characteristics of blind pedestrians and their interactions with both the navigation aid (e.g., a white cane or a guide dog) and the environment. We benchmark state-of-the-art 3D human prediction models, finding poor performance with off-the-shelf and pre-training-based methods for our novel task. To contribute toward safer and more reliable systems that can seamlessly reason over diverse human movements in their environments, our text-and-motion benchmark is available at https://blindways.github.io/.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"16272-16285"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12013345/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps. 海马体-内嗅回路的结合使认知地图具有组合性。

Advances in neural information processing systems Pub Date : 2024-01-01

Christopher J Kymn, Sonia Mazelet, Anthony Thomas, Denis Kleyko, E Paxon Frady, Friedrich T Sommer, Bruno A Olshausen

{"title":"Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps.","authors":"Christopher J Kymn, Sonia Mazelet, Anthony Thomas, Denis Kleyko, E Paxon Frady, Friedrich T Sommer, Bruno A Olshausen","doi":"","DOIUrl":"","url":null,"abstract":"We propose a normative model for spatial representation in the hippocampal formation that combines optimality principles, such as maximizing coding range and spatial information per neuron, with an algebraic framework for computing in distributed representation. Spatial position is encoded in a residue number system, with individual residues represented by high-dimensional, complex-valued vectors. These are composed into a single vector representing position by a similarity-preserving, conjunctive vector-binding operation. Self-consistency between the representations of the overall position and of the individual residues is enforced by a modular attractor network whose modules correspond to the grid cell modules in entorhinal cortex. The vector binding operation can also associate different contexts to spatial representations, yielding a model for entorhinal cortex and hippocampus. We show that the model achieves normative desiderata including superlinear scaling of patterns with dimension, robust error correction, and hexagonal, carry-free encoding of spatial position. These properties in turn enable robust path integration and association with sensory inputs. More generally, the model formalizes how compositional computations could occur in the hippocampal formation and leads to testable experimental predictions.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"39128-39157"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12183976/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144478028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Recurrent neural network dynamical systems for biological vision. 生物视觉的递归神经网络动态系统。

Advances in neural information processing systems Pub Date : 2024-01-01

Wayne W M Soo, Aldo Battista, Puria Radmard, Xiao-Jing Wang

{"title":"Recurrent neural network dynamical systems for biological vision.","authors":"Wayne W M Soo, Aldo Battista, Puria Radmard, Xiao-Jing Wang","doi":"","DOIUrl":"","url":null,"abstract":"In neuroscience, recurrent neural networks (RNNs) are modeled as continuous-time dynamical systems to more accurately reflect the dynamics inherent in biological circuits. However, convolutional neural networks (CNNs) remain the preferred architecture in vision neuroscience due to their ability to efficiently process visual information, which comes at the cost of the biological realism provided by RNNs. To address this, we introduce a hybrid architecture that integrates the continuous-time recurrent dynamics of RNNs with the spatial processing capabilities of CNNs. Our models preserve the dynamical characteristics typical of RNNs while having comparable performance with their conventional CNN counterparts on benchmarks like ImageNet. Compared to conventional CNNs, our models demonstrate increased robustness to noise due to noise-suppressing mechanisms inherent in recurrent dynamical systems. Analyzing our architecture as a dynamical system is computationally expensive, so we develop a toolkit consisting of iterative methods specifically tailored for convolutional structures. We also train multi-area RNNs using our architecture as the front-end to perform complex cognitive tasks previously impossible to learn or achievable only with oversimplified stimulus representations. In monkey neural recordings, our models capture time-dependent variations in neural activity in higher-order visual areas. Together, these contributions represent a comprehensive foundation to unify the advances of CNNs and dynamical RNNs in vision neuroscience.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"135966-135982"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12448710/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145115065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards a "universal translator" for neural dynamics at single-cell, single-spike resolution. 迈向单细胞、单尖峰分辨率的神经动力学“通用翻译器”。

Advances in neural information processing systems Pub Date : 2024-01-01

Yizi Zhang, Yanchen Wang, Donato M Jiménez-Benetó, Zixuan Wang, Mehdi Azabou, Blake Richards, Renee Tung, Olivier Winter, Eva Dyer, Liam Paninski, Cole Hurwitz

{"title":"Towards a \"universal translator\" for neural dynamics at single-cell, single-spike resolution.","authors":"Yizi Zhang, Yanchen Wang, Donato M Jiménez-Benetó, Zixuan Wang, Mehdi Azabou, Blake Richards, Renee Tung, Olivier Winter, Eva Dyer, Liam Paninski, Cole Hurwitz","doi":"","DOIUrl":"","url":null,"abstract":"Neuroscience research has made immense progress over the last decade, but our understanding of the brain remains fragmented and piecemeal: the dream of probing an arbitrary brain region and automatically reading out the information encoded in its neural activity remains out of reach. In this work, we build towards a first foundation model for neural spiking data that can solve a diverse set of tasks across multiple brain areas. We introduce a novel self-supervised modeling approach for population activity in which the model alternates between masking out and reconstructing neural activity across different time steps, neurons, and brain regions. To evaluate our approach, we design unsupervised and supervised prediction tasks using the International Brain Laboratory repeated site dataset, which is comprised of Neuropixels recordings targeting the same brain locations across 48 animals and experimental sessions. The prediction tasks include single-neuron and region-level activity prediction, forward prediction, and behavior decoding. We demonstrate that our multi-task-masking (MtM) approach significantly improves the performance of current state-of-the-art population models and enables multitask learning. We also show that by training on multiple animals, we can improve the generalization ability of the model to unseen animals, paving the way for a foundation model of the brain at single-cell, single-spike resolution. Project page and code: https://ibl-mtm.github.io/.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"80495-80521"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12228527/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144577102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fairness-Aware Estimation of Graphical Models. 图形模型的公平感知估计。

Advances in neural information processing systems Pub Date : 2024-01-01

Zhuoping Zhou, Davoud Ataee Tarzanagh, Bojian Hou, Qi Long, Li Shen

引用次数: 0

OccFusion: Rendering Occluded Humans with Generative Diffusion Priors. 遮蔽：用生成扩散先验渲染遮挡的人类。

Advances in neural information processing systems Pub Date : 2024-01-01

Adam Sun, Tiange Xiang, Scott Delp, Li Fei-Fei, Ehsan Adeli

引用次数: 0