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

Score-Based Diffusion Modeling for Nonparametric Empirical Bayes in Heteroscedastic Gaussian Mixtures. 异方差高斯混合中非参数经验贝叶斯的基于分数的扩散建模。

Advances in neural information processing systems Pub Date : 2025-01-01 DOI: 10.52202/085713-3753

Gongyu Chen, Ying Cui

{"title":"Score-Based Diffusion Modeling for Nonparametric Empirical Bayes in Heteroscedastic Gaussian Mixtures.","authors":"Gongyu Chen, Ying Cui","doi":"10.52202/085713-3753","DOIUrl":"https://doi.org/10.52202/085713-3753","url":null,"abstract":"We propose a generalized score-based diffusion framework for learning multivariate Gaussian mixture models with homoscedastic or heteroscedastic noise. Our goal is to nonparametrically estimate the latent location distribution and denoise the observations. Departing from the conventional maximum likelihood approach, we reinterpret each observation as a temporal slice of a family of stochastic diffusion processes. This modeling choice enables a principled characterization of the additive noise structure and supports a multi-step denoising procedure grounded in reverse-time dynamics. We introduce a score-based objective that explicitly models the latent distribution and accommodates observation-specific noise covariances. Theoretically, we establish that the score estimation error with <math><mi>n</mi></math> independent observations achieves a near-parametric error rate of <math> <mfrac><mrow><mtext>polylog</mtext> <mspace></mspace> <mo>(</mo> <mi>n</mi> <mo>)</mo></mrow> <mrow><mi>n</mi></mrow> </mfrac> </math> , improving upon existing results in the diffusion literature. Empirically, our method outperforms the nonparametric maximum likelihood estimator in both density estimation and denoising fidelity, especially in high-dimensional settings. These findings suggest a promising direction for integrating nonparametric empirical Bayes with diffusion-based generative modeling for latent structure recovery.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"124577-124613"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13626175/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119113","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

Adaptive Time Encoding for Irregular Multivariate Time-Series Classification. 不规则多元时间序列分类的自适应时间编码。

Advances in neural information processing systems Pub Date : 2025-01-01

Sangho Lee, Kyeongseo Min, Youngdoo Son, Hyungrok Do

引用次数: 0

Latent Chain-of-Thought for Visual Reasoning. 视觉推理的潜在思维链。

Advances in neural information processing systems Pub Date : 2025-01-01

Guohao Sun, Hang Hua, Jian Wang, Jiebo Luo, Sohail Dianat, Majid Rabbani, Raghuveer Rao, Zhiqiang Tao

{"title":"Latent Chain-of-Thought for Visual Reasoning.","authors":"Guohao Sun, Hang Hua, Jian Wang, Jiebo Luo, Sohail Dianat, Majid Rabbani, Raghuveer Rao, Zhiqiang Tao","doi":"","DOIUrl":"","url":null,"abstract":"Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen reasoning tasks and heavily rely on a biased reward model. To address this challenge, we reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference. By leveraging diversity-seeking reinforcement learning algorithms, we introduce a novel sparse reward function for token-level learning signals that encourage diverse, high-likelihood latent CoT, overcoming deterministic sampling limitations and avoiding reward hacking. Additionally, we implement a Bayesian inference-scaling strategy that replaces costly Best-of-N and Beam Search with a marginal likelihood to efficiently rank optimal rationales and answers. We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks, in terms of effectiveness, generalization, and interpretability. The code is available at https://github.com/heliossun/LaCoT.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"103739-103762"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13170605/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147943965","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

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments. 深度强化学习需要深度行为分析：探索开放式环境中无模型智能体的隐式规划。

Advances in neural information processing systems Pub Date : 2025-01-01

Riley Simmons-Edler, Ryan P Badman, Felix Baastad Berg, Raymond Chua, John J Vastola, Joshua Lunger, William Qian, Kanaka Rajan

{"title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments.","authors":"Riley Simmons-Edler, Ryan P Badman, Felix Baastad Berg, Raymond Chua, John J Vastola, Joshua Lunger, William Qian, Kanaka Rajan","doi":"","DOIUrl":"","url":null,"abstract":"Understanding the behavior of deep reinforcement learning (DRL) agents-particularly as task and agent sophistication increase-requires more than simple comparison of reward curves, yet standard methods for behavioral analysis remain underdeveloped in DRL. We apply tools from neuroscience and ethology to study DRL agents in a novel, complex, partially observable environment, ForageWorld, designed to capture key aspects of real-world animal foraging-including sparse, depleting resource patches, predator threats, and spatially extended arenas. We use this environment as a platform for applying joint behavioral and neural analysis to agents, revealing detailed, quantitatively grounded insights into agent strategies, memory, and planning. Contrary to common assumptions, we find that model-free RNN-based DRL agents can exhibit structured, planning-like behavior purely through emergent dynamics-without requiring explicit memory modules or world models. Our results show that studying DRL agents like animals-analyzing them with neuroethology-inspired tools that reveal structure in both behavior and neural dynamics-uncovers rich structure in their learning dynamics that would otherwise remain invisible. We distill these tools into a general analysis framework linking core behavioral and representational features to diagnostic methods, which can be reused for a wide range of tasks and agents. As agents grow more complex and autonomous, bridging neuroscience, cognitive science, and AI will be essential-not just for understanding their behavior, but for ensuring safe alignment and maximizing desirable behaviors that are hard to measure via reward. We show how this can be done by drawing on lessons from how biological intelligence is studied.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"81066-81113"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13151939/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870784","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

On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection. 拟合优度检验在水印检测中的经验作用。

Advances in neural information processing systems Pub Date : 2025-01-01

Weiqing He, Xiang Li, Tianqi Shang, Li Shen, Weijie Su, Qi Long

引用次数: 0

Optical Coherence Tomography Harmonization with Anatomy-Guided Latent Metric Schrödinger Bridges. 光学相干层析成像与解剖引导隐度量协调Schrödinger桥。

Advances in neural information processing systems Pub Date : 2025-01-01

Shuwen Wei, Samuel W Remedios, Blake E Dewey, Zhangxing Bian, Shimeng Wang, Junyu Chen, Bruno M Jedynak, Shiv Saidha, Peter A Calabresi, Aaron Carass, Jerry L Prince

{"title":"Optical Coherence Tomography Harmonization with Anatomy-Guided Latent Metric Schrödinger Bridges.","authors":"Shuwen Wei, Samuel W Remedios, Blake E Dewey, Zhangxing Bian, Shimeng Wang, Junyu Chen, Bruno M Jedynak, Shiv Saidha, Peter A Calabresi, Aaron Carass, Jerry L Prince","doi":"","DOIUrl":"","url":null,"abstract":"Medical image harmonization aims to reduce the differences in appearance caused by scanner hardware variations to allow for consistent and reliable comparisons across devices. Harmonization based on paired images from different devices has limited applicability in real-world clinical settings. On the other hand, unpaired harmonization typically does not guarantee anatomy consistency, which is problematic because anatomical information preservation is paramount. The Schrödinger bridge framework has achieved state-of-the-art style transfer performance with natural images by matching distributions of unpaired images, but this approach can also introduce anatomy changes when applied to medical images. We show that such changes occur because the Schrödinger bridge uses the square of the Euclidean distance between images as the transport cost in an entropy-regularized optimal transport problem. Such a transport cost is not appropriate for measuring anatomical distances, as medical images with the same anatomy need not have a small Euclidean distance between them. In this paper, we propose a latent metric Schrödinger bridge (LMSB) framework to improve the anatomical consistency for the harmonization of medical images. We develop an invertible network that maps medical images into a latent Euclidean metric space where the distances among images with the same anatomy are minimized using the pullback latent metric. Within this latent space, we train a Schrödinger bridge to match distributions. We show that the proposed LMSB is superior to the direct application of a Schrödinger bridge to harmonize optical coherence tomography (OCT) images.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"5716-5744"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13352978/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148427004","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

Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder. 识别跨大脑区域的相互作用，同时利用基于变压器的变分自编码器计算个体神经元动态。

Advances in neural information processing systems Pub Date : 2025-01-01 DOI: 10.52202/085713-3968

Qi Xin, Robert E Kass

{"title":"Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder.","authors":"Qi Xin, Robert E Kass","doi":"10.52202/085713-3968","DOIUrl":"10.52202/085713-3968","url":null,"abstract":"Advances in large-scale recording technologies now enable simultaneous measurements from multiple brain areas, offering new opportunities to study signal transmission across interacting components of neural circuits. However, neural responses exhibit substantial trial-to-trial variability, often driven by unobserved factors such as subtle changes in animal behavior or internal states. To prevent evolving background dynamics from contaminating identification of functional coupling, we developed a hybrid neural spike train model, GLM-Transformer, that incorporates flexible, deep latent variable models into a point process generalized linear model (GLM) having an interpretable component for cross-population interactions. A Transformer-based variational autoencoder captures nonstationary individual-neuron dynamics that vary across trials, while standard nonparametric regression GLM coupling terms provide estimates of directed interactions between neural populations. We incorporate a low-rank structure on population-to-population coupling effects to improve scalability. Across synthetic datasets and mechanistic simulations, GLM-Transformer recovers known coupling structure and remains robust to shared background fluctuations. When applied to the Allen Institute Visual Coding dataset, it identifies feedforward pathways consistent with established visual hierarchy. This work offers a step toward improved identification of neural population interactions, and contributes to ongoing efforts aimed at achieving interpretable results while harvesting the benefits of deep learning.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"131831-131856"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13573293/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148972569","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

Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules. 梯度下降作为损失景观导航：导出学习规则的规范框架。

Advances in neural information processing systems Pub Date : 2025-01-01

John J Vastola, Samuel J Gershman, Kanaka Rajan

{"title":"Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules.","authors":"John J Vastola, Samuel J Gershman, Kanaka Rajan","doi":"","DOIUrl":"","url":null,"abstract":"Learning rules-prescriptions for updating model parameters to improve performance-are typically assumed rather than derived. Why do some learning rules work better than others, and under what assumptions can a given rule be considered optimal? We propose a theoretical framework that casts learning rules as policies for navigating (partially observable) loss landscapes, and identifies optimal rules as solutions to an associated optimal control problem. A range of well-known rules emerge naturally within this framework under different assumptions: gradient descent from short-horizon optimization, momentum from longer-horizon planning, natural gradients from accounting for parameter space geometry, non-gradient rules from partial controllability, and adaptive optimizers like Adam from online Bayesian inference of loss landscape shape. We further show that continual learning strategies like weight resetting can be understood as optimal responses to task uncertainty. By unifying these phenomena under a single objective, our framework clarifies the computational structure of learning and offers a principled foundation for designing adaptive algorithms.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"119609-119650"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13151920/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870830","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

Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference. 基于实时推理的多尺度神经活动非线性潜在因素动态建模。

Advances in neural information processing systems Pub Date : 2025-01-01 DOI: 10.52202/085713-0927

Eray Erturk, Maryam M Shanechi

{"title":"Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference.","authors":"Eray Erturk, Maryam M Shanechi","doi":"10.52202/085713-0927","DOIUrl":"10.52202/085713-0927","url":null,"abstract":"Real-time decoding of target variables from multiple simultaneously recorded neural time-series modalities, such as discrete spiking activity and continuous field potentials, is important across various neuroscience applications. However, a major challenge for doing so is that different neural modalities can have different timescales (i.e., sampling rates) and different probabilistic distributions, or can even be missing at some time-steps. Existing nonlinear models of multimodal neural activity do not address different timescales or missing samples across modalities. Further, some of these models do not allow for real-time decoding. Here, we develop a learning framework that can enable real-time recursive decoding while nonlinearly aggregating information across multiple modalities with different timescales and distributions and with missing samples. This framework consists of 1) a multiscale encoder that nonlinearly aggregates information after learning within-modality dynamics to handle different timescales and missing samples in real time, 2) a multiscale dynamical backbone that extracts multimodal temporal dynamics and enables real-time recursive decoding, and 3) modality-specific decoders to account for different probabilistic distributions across modalities. In both simulations and three distinct multiscale brain datasets, we show that our model can aggregate information across modalities with different timescales and distributions and missing samples to improve real-time target decoding. Further, our method outperforms various linear and nonlinear multimodal benchmarks in doing so.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"31271-31310"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13521588/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842353","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

Flexible inference for animal learning rules using neural networks. 基于神经网络的动物学习规则灵活推理。

Advances in neural information processing systems Pub Date : 2025-01-01

Yuhan Helena Liu, Victor Geadah, Jonathan Pillow

{"title":"Flexible inference for animal learning rules using neural networks.","authors":"Yuhan Helena Liu, Victor Geadah, Jonathan Pillow","doi":"","DOIUrl":"","url":null,"abstract":"Understanding how animals learn is a central challenge in neuroscience, with growing relevance to the development of animal- or human-aligned artificial intelligence. However, existing approaches tend to assume fixed parametric forms for the learning rule (e.g., Q-learning, policy gradient), which may not accurately describe the complex forms of learning employed by animals in realistic settings. Here we address this gap by developing a framework to infer learning rules directly from behavioral data collected during de novo task learning. We assume that animals follow a decision policy parameterized by a generalized linear model (GLM), and we model their learning rule-the mapping from task covariates to per-trial weight updates-using a deep neural network (DNN). This formulation allows flexible, data-driven inference of learning rules while maintaining an interpretable form of the decision policy itself. To capture more complex learning dynamics, we introduce a recurrent neural network (RNN) variant that relaxes the Markovian assumption that learning depends solely on covariates of the current trial, allowing for learning rules that integrate information over multiple trials. Simulations demonstrate that the framework can recover ground-truth learning rules. We applied our DNN and RNN-based methods to a large behavioral dataset from mice learning to perform a sensory decision-making task and found that they outperformed traditional RL learning rules at predicting the learning trajectories of held-out mice. The inferred learning rules exhibited reward-history-dependent learning dynamics, with larger updates following sequences of rewarded trials. Overall, these methods provide a flexible framework for inferring learning rules from behavioral data in de novo learning tasks, setting the stage for improved animal training protocols and the development of behavioral digital twins.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"8691-8729"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13417974/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148622742","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