We prove that a single-layer neural network trained with the online actor critic algorithm converges in distribution to a random ordinary differential equation (ODE) as the number of hidden units and the number of training steps $\rightarrow \infty$. In the online actor-critic algorithm, the distribution of the data samples dynamically changes as the model is updated, which is a key challenge for any convergence analysis. We establish the geometric ergodicity of the data samples under a fixed actor policy. Then, using a Poisson equation, we prove that the fluctuations of the model updates around the limit distribution due to the randomly-arriving data samples vanish as the number of parameter updates $\rightarrow \infty$. Using the Poisson equation and weak convergence techniques, we prove that the actor neural network and critic neural network converge to the solutions of a system of ODEs with random initial conditions. Analysis of the limit ODE shows that the limit critic network will converge to the true value function, which will provide the actor an asymptotically unbiased estimate of the policy gradient. We then prove that the limit actor network will converge to a stationary point.
相關內容
Networking：IFIP International Conferences on Networking。
Explanation：國際網絡會議。
Publisher：IFIP。
SIT：
As artificial intelligence becomes increasingly prevalent in scientific research, data-driven methodologies appear to overshadow traditional methods in resolving scientific problems. In this Perspective, we revisit a classic classification of scientific problems and rethink the evolution of scientific paradigms from the standpoint of data, algorithms, and computational power. We observe that the strengths of new paradigms have expanded the range of resolvable scientific problems, but the continued advancement of data, algorithms, and computational power is unlikely to bring a new paradigm. To tackle unresolved problems of organised complexity in more intricate systems, we argue that the integration of paradigms is a promising approach. Consequently, we propose behavioural rehearsing, checking what will happen in such systems through multiple times of simulation. One of the methodologies to realise it, sophisticated behavioural simulation (SBS), represents a higher level of paradigms integration based on foundational models to simulate complex social systems involving sophisticated human strategies and behaviours. SBS extends beyond the capabilities of traditional agent-based modelling simulation (ABMS), and therefore, makes behavioural rehearsing a potential solution to problems of organised complexity in complex human systems.
Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning. The retrieved information is incorporated into LMs as context alongside the query, enhancing the reliability of responses towards factual questions. Prior researches in retrieval augmentation typically follow a retriever-generator paradigm. In this context, traditional retrievers encounter challenges in precisely and seamlessly extracting query-relevant information from knowledge bases. To address this issue, this paper introduces a novel retrieval augmentation framework called ChatLR that primarily employs the powerful semantic understanding ability of Large Language Models (LLMs) as retrievers to achieve precise and concise information retrieval. Additionally, we construct an LLM-based search and question answering system tailored for the financial domain by fine-tuning LLM on two tasks including Text2API and API-ID recognition. Experimental results demonstrate the effectiveness of ChatLR in addressing user queries, achieving an overall information retrieval accuracy exceeding 98.8\%.
Given the high spectral efficiency, holographic multiple-input multiple-output (MIMO) technology holds promise for enhancing both sensing and communication capabilities. However, accurately characterizing its performance poses a challenge due to the spatial correlation induced by densely spaced antennas. In this paper, a holographic MIMO (HMIMO) based integrated sensing and communications (ISAC) framework is proposed for both downlink and uplink scenarios. The spacial correlation is incorporated in the communication channel modeling, while an accurate spherical wave-based model is utilized to characterize sensing link. By considering both instantaneous channel state information (CSI) and statistical CSI, closed-form expressions are derived for sensing rates (SRs), communication rates (CRs), and outage probabilities under different ISAC designs to investigate the theoretical performance limits of the proposed HISAC framework. Further insights are gained by examining high signal-to-noise ratio slopes and diversity orders. Specifically, i) for the downlink case, a sensing-centric (S-C) design and a communications-centric (C-C) design are investigated based on different beamforming strategies, and a Pareto optimal design is proposed to characterize the attainable SR-CR region; ii) for the uplink case, the S-C design and the C-C design are distinguished by the interference cancellation order of the communication signal and the sensing signal, and the rate region is obtained through a time-sharing strategy. Numerical results reveal that HMIMO based ISAC (HISAC) systems outperform both conventional MIMO based ISAC systems and HMIMO based frequency-division sensing and communications systems, underscoring the superior performance of HISAC.
We propose a new Bayesian heteroskedastic Markov-switching structural vector autoregression with data-driven time-varying identification. The model selects alternative exclusion restrictions over time and, as a condition for the search, allows to verify identification through heteroskedasticity within each regime. Based on four alternative monetary policy rules, we show that a monthly six-variable system supports time variation in US monetary policy shock identification. In the sample-dominating first regime, systematic monetary policy follows a Taylor rule extended by the term spread, effectively curbing inflation. In the second regime, occurring after 2000 and gaining more persistence after the global financial and COVID crises, it is characterized by a money-augmented Taylor rule. This regime's unconventional monetary policy provides economic stimulus, features the liquidity effect, and is complemented by a pure term spread shock. Absent the specific monetary policy of the second regime, inflation would be over one percentage point higher on average after 2008.
We explore the social and contextual factors that influence the outcome of person-to-person music recommendations and discovery. Specifically, we use data from Spotify to investigate how a link sent from one user to another results in the receiver engaging with the music of the shared artist. We consider several factors that may influence this process, such as the strength of the sender-receiver relationship, the user's role in the Spotify social network, their music social cohesion, and how similar the new artist is to the receiver's taste. We find that the receiver of a link is more likely to engage with a new artist when (1) they have similar music taste to the sender and the shared track is a good fit for their taste, (2) they have a stronger and more intimate tie with the sender, and (3) the shared artist is popular amongst the receiver's connections. Finally, we use these findings to build a Random Forest classifier to predict whether a shared music track will result in the receiver's engagement with the shared artist. This model elucidates which type of social and contextual features are most predictive, although peak performance is achieved when a diverse set of features are included. These findings provide new insights into the multifaceted mechanisms underpinning the interplay between music discovery and social processes.
With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. With Large Language Models (LLMs) showcasing remarkable capabilities in key language tasks, this survey provides a detailed overview of the recent advancements in video understanding harnessing the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended spatial-temporal reasoning combined with commonsense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into four main types: LLM-based Video Agents, Vid-LLMs Pretraining, Vid-LLMs Instruction Tuning, and Hybrid Methods. Furthermore, this survey also presents a comprehensive study of the tasks and datasets for Vid-LLMs, along with the methodologies employed for evaluation. Additionally, the survey explores the expansive applications of Vid-LLMs across various domains, thereby showcasing their remarkable scalability and versatility in addressing challenges in real-world video understanding. Finally, the survey summarizes the limitations of existing Vid-LLMs and the directions for future research. For more information, we recommend readers visit the repository at //github.com/yunlong10/Awesome-LLMs-for-Video-Understanding.
Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs). This link relies on the convergence of network weights to a smooth function as the number of layers increases. We investigate the properties of weights trained by stochastic gradient descent and their scaling with network depth through detailed numerical experiments. We observe the existence of scaling regimes markedly different from those assumed in neural ODE literature. Depending on certain features of the network architecture, such as the smoothness of the activation function, one may obtain an alternative ODE limit, a stochastic differential equation or neither of these. These findings cast doubts on the validity of the neural ODE model as an adequate asymptotic description of deep ResNets and point to an alternative class of differential equations as a better description of the deep network limit.
We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to space-time. Our objective encourages temporally-persistent features in the same video, and in spite of its simplicity, it works surprisingly well across: (i) different unsupervised frameworks, (ii) pre-training datasets, (iii) downstream datasets, and (iv) backbone architectures. We draw a series of intriguing observations from this study, e.g., we discover that encouraging long-spanned persistency can be effective even if the timespan is 60 seconds. In addition to state-of-the-art results in multiple benchmarks, we report a few promising cases in which unsupervised pre-training can outperform its supervised counterpart. Code is made available at //github.com/facebookresearch/SlowFast
Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise. Therefore, eliminating the impact of distribution shifts between training and testing data is crucial for building performance-promising deep models. Conventional methods assume either the known heterogeneity of training data (e.g. domain labels) or the approximately equal capacities of different domains. In this paper, we consider a more challenging case where neither of the above assumptions holds. We propose to address this problem by removing the dependencies between features via learning weights for training samples, which helps deep models get rid of spurious correlations and, in turn, concentrate more on the true connection between discriminative features and labels. Extensive experiments clearly demonstrate the effectiveness of our method on multiple distribution generalization benchmarks compared with state-of-the-art counterparts. Through extensive experiments on distribution generalization benchmarks including PACS, VLCS, MNIST-M, and NICO, we show the effectiveness of our method compared with state-of-the-art counterparts.
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis, thereby allowing manual manipulation in predicting the final answer.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191