arXiv subjects

Di Yu

Publications and source records attributed to Di Yu.

29 records · Page 2Linked to original sources

arXiv2025

Dendritic Localized Learning: Toward Biologically Plausible Algorithm

Backpropagation is the foundational algorithm for training neural networks and a key driver of deep learning's success. However, its biological plausibility has been challenged due to three primary limitations: weight symmetry, reliance on global error signals, and the dual-phase nature of training, as highlighted by the existing literature. Although various alternative learning approaches have been proposed to address these issues, most either fail to satisfy all three criteria simultaneously or yield suboptimal results. Inspired by the dynamics and plasticity of pyramidal neurons, we propose Dendritic Localized Learning (DLL), a novel learning algorithm designed to overcome these challenges. Extensive empirical experiments demonstrate that DLL satisfies all three criteria of biological plausibility while achieving state-of-the-art performance among algorithms that meet these requirements. Furthermore, DLL exhibits strong generalization across a range of architectures, including MLPs, CNNs, and RNNs. These results, benchmarked against existing biologically plausible learning algorithms, offer valuable empirical insights for future research. We hope this study can inspire the development of new biologically plausible algorithms for training multilayer networks and advancing progress in both neuroscience and machine learning. Our code is available at https://github.com/Lvchangze/Dendritic-Localized-Learning.

cs.NE↗

arXiv2024

Exploiting Label Skewness for Spiking Neural Networks in Federated Learning

The energy efficiency of deep spiking neural networks (SNNs) aligns with the constraints of resource-limited edge devices, positioning SNNs as a promising foundation for intelligent applications leveraging the extensive data collected by these devices. To address data privacy concerns when deploying SNNs on edge devices, federated learning (FL) facilitates collaborative model training by leveraging data distributed across edge devices without transmitting local data to a central server. However, existing FL approaches struggle with label-skewed data across devices, which leads to drift in local SNN models and degrades the performance of the global SNN model. In this paper, we propose a novel framework called FedLEC, which incorporates intra-client label weight calibration to balance the learning intensity across local labels and inter-client knowledge distillation to mitigate local SNN model bias caused by label absence. Extensive experiments with three different structured SNNs across five datasets (i.e., three non-neuromorphic and two neuromorphic datasets) demonstrate the efficiency of FedLEC. Compared to eight state-of-the-art FL algorithms, FedLEC achieves an average accuracy improvement of approximately 11.59% for the global SNN model under various label skew distribution settings.

cs.LG↗

arXiv2024

Deterministic and Stochastic Frank-Wolfe Recursion on Probability Spaces

Motivated by applications in emergency response and experimental design, we consider smooth stochastic optimization problems over probability measures supported on compact subsets of the Euclidean space. With the influence function as the variational object, we construct a deterministic Frank-Wolfe (dFW) recursion for probability spaces, made especially possible by a lemma that identifies a ``closed-form'' solution to the infinite-dimensional Frank-Wolfe sub-problem. Each iterate in dFW is expressed as a convex combination of the incumbent iterate and a Dirac measure concentrating on the minimum of the influence function at the incumbent iterate. To address common application contexts that have access only to Monte Carlo observations of the objective and influence function, we construct a stochastic Frank-Wolfe (sFW) variation that generates a random sequence of probability measures constructed using minima of increasingly accurate estimates of the influence function. We demonstrate that sFW's optimality gap sequence exhibits $O(k^{-1})$ iteration complexity almost surely and in expectation for smooth convex objectives, and $O(k^{-1/2})$ (in Frank-Wolfe gap) for smooth non-convex objectives. Furthermore, we show that an easy-to-implement fixed-step, fixed-sample version of (sFW) exhibits exponential convergence to $\varepsilon$-optimality. We end with a central limit theorem on the observed objective values at the sequence of generated random measures. To further intuition, we include several illustrative examples with exact influence function calculations.

math.OC↗

arXiv2024

Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection

Nonlinear dimensionality reduction lacks interpretability due to the absence of source features in low-dimensional embedding space. We propose an interpretable method featMAP to preserve source features by tangent space embedding. The core of our proposal is to utilize local singular value decomposition (SVD) to approximate the tangent space which is embedded to low-dimensional space by maintaining the alignment. Based on the embedding tangent space, featMAP enables the interpretability by locally demonstrating the source features and feature importance. Furthermore, featMAP embeds the data points by anisotropic projection to preserve the local similarity and original density. We apply featMAP to interpreting digit classification, object detection and MNIST adversarial examples. FeatMAP uses source features to explicitly distinguish the digits and objects and to explain the misclassification of adversarial examples. We also compare featMAP with other state-of-the-art methods on local and global metrics.

cs.CV↗

arXiv2023

Symmetry-Based Quantum Circuit Mapping

Quantum circuit mapping is a crucial process in the quantum circuit compilation pipeline, facilitating the transformation of a logical quantum circuit into a list of instructions directly executable on a target quantum system. Recent research has introduced a post-compilation step known as remapping, which seeks to reconfigure the initial circuit mapping to mitigate quantum circuit errors arising from system variability. As quantum processors continue to scale in size, the efficiency of quantum circuit mapping and the overall compilation process has become of paramount importance. In this work, we introduce a quantum circuit remapping algorithm that leverages the intrinsic symmetries in quantum processors, making it well-suited for large-scale quantum systems. This algorithm identifies all topologically equivalent circuit mappings by constraining the search space using symmetries and accelerates the scoring of each mapping using vector computation. Notably, this symmetry-based circuit remapping algorithm exhibits linear scaling with the number of qubits in the target quantum hardware and is proven to be optimal in terms of its time complexity. Moreover, we conduct a comparative analysis against existing methods in the literature, demonstrating the superior performance of our symmetry-based method on state-of-the-art quantum hardware architectures and highlighting the practical utility of our algorithm, particularly for quantum processors with millions of qubits.

quant-ph↗

arXiv2023

Impact of transforming interface geometry on edge states in valley photonic crystals

Topologically protected edge states arise at the interface of two topologically distinct valley photonic crystals. In this work, we investigate how tailoring the interface geometry, specifically from a zigzag interface to a glide plane, profoundly affects these edge states. Near-field measurements demonstrate how this transformation significantly changes the dispersion relation of the edge mode. We observe a transition from gapless edge states to gapped ones, accompanied by the occurrence of slow light within the Brillouin zone, rather than at its edge. Additionally, we simulate the propagation of the modified edge states through a specially designed valley-conserving defect. The simulations show, by monitoring the transmittance of this defect, how the robustness to backscattering gradually decreases, suggesting a disruption of valley-dependent transport. These findings demonstrate how the gradual emergence of valley-dependent gapless edge states in a valley photonic crystal depends on the geometry of its interface.

physics.optics↗

arXiv2023

Using Adamic-Adar Index Algorithm to Predict Volunteer Collaboration: Less is More

Social networks exhibit a complex graph-like structure due to the uncertainty surrounding potential collaborations among participants. Machine learning algorithms possess generic outstanding performance in multiple real-world prediction tasks. However, whether machine learning algorithms outperform specific algorithms designed for graph link prediction remains unknown to us. To address this issue, the Adamic-Adar Index (AAI), Jaccard Coefficient (JC) and common neighbour centrality (CNC) as representatives of graph-specific algorithms were applied to predict potential collaborations, utilizing data from volunteer activities during the Covid-19 pandemic in Shenzhen city, along with the classical machine learning algorithms such as random forest, support vector machine, and gradient boosting as single predictors and components of ensemble learning. This paper introduces that the AAI algorithm outperformed the traditional JC and CNC, and other machine learning algorithms in analyzing graph node attributes for this task.

cs.SI↗

arXiv2022

DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation

Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison. We, therefore, conduct studies from the perspectives of practical theory and experiments, aiming at benchmarking recommendation for rigorous evaluation. Regarding the theoretical study, a series of hyper-factors affecting recommendation performance throughout the whole evaluation chain are systematically summarized and analyzed via an exhaustive review on 141 papers published at eight top-tier conferences within 2017-2020. We then classify them into model-independent and model-dependent hyper-factors, and different modes of rigorous evaluation are defined and discussed in-depth accordingly. For the experimental study, we release DaisyRec 2.0 library by integrating these hyper-factors to perform rigorous evaluation, whereby a holistic empirical study is conducted to unveil the impacts of different hyper-factors on recommendation performance. Supported by the theoretical and experimental studies, we finally create benchmarks for rigorous evaluation by proposing standardized procedures and providing performance of ten state-of-the-arts across six evaluation metrics on six datasets as a reference for later study. Overall, our work sheds light on the issues in recommendation evaluation, provides potential solutions for rigorous evaluation, and lays foundation for further investigation.

cs.IR↗

arXiv2020

Perturbation theory for Maxwell's equations in anisotropic materials with shifting boundaries

Perturbation theory is a kind of estimation method based on theorem of Taylor expansion, and is useful to investigate electromagnetic solutions of small changes. By considering a sharp boundary as a limit of smoothed systems, previous study has solved the problem when applying standard perturbation theory to Maxwell's equations for small shifts in isotropic dielectric interfaces. However, when dealing with anisotropic materials, an approximation is conducted and leads to an unsatisfactory error. Here we develop a modified perturbation theory for small shifts in anisotropically dielectric interfaces. By using optimized smoothing function for each component of permittivity, we obtain a method to calculate the intrinsic frequency shifts of anisotropic permittivity field when boundaries shift, without approximation. Our method shows accurate results when calculating eigenfrequency's shifts in strong-anisotropy materials, and can be widely used for small shifts in anisotropically dielectric interfaces.

physics.comp-ph↗

arXiv2020

Phonon mediated non-equilibrium correlations and entanglement between distant semiconducting qubits

We theoretically study the non-equilibrium correlations and entanglement between distant semiconductor qubits in a one-dimensional coupled-mechanical-resonator chain. Each qubit is defined by a double quantum dot (DQD) and embedded in a mechanical resonator. The two qubits can be coupled, correlated and entangled through phonon transfer along the resonator chain. We calculate the non-equilibrium correlations and steady-state entanglement at different phonon-phonon coupling rates, and find a maximal steady entanglement induced by a population inversion. The results suggest that highly tunable correlations and entanglement can be generated by phonon-qubit hybrid system, which will contribute to the development of mesoscopic physics and solid-state quantum computation.

cond-mat.mes-hall↗

arXiv2019

Automating Data Monitoring: Detecting Structural Breaks in Time Series Data Using Bayesian Minimum Description Length

In modern business modeling and analytics, data monitoring plays a critical role. Nowadays, sophisticated models often rely on hundreds or even thousands of input variables. Over time, structural changes such as abrupt level shifts or trend slope changes may occur among some of these variables, likely due to changes in economy or government policies. As a part of data monitoring, it is important to identify these changepoints, in terms of which variables exhibit such changes, and what time locations do the changepoints occur. Being alerted about the changepoints can help modelers decide if models need modification or rebuilds, while ignoring them may increase risks of model degrading. Simple process control rules often flag too many false alarms because regular seasonal fluctuations or steady upward or downward trends usually trigger alerts. To reduce potential false alarms, we create a novel statistical method based on the Bayesian Minimum Description Length (BMDL) framework to perform multiple change-point detection. Our method is capable of detecting all structural breaks occurred in the past, and automatically handling data with or without seasonality and/or autocorrelation. It is implemented with computation algorithms such as Markov chain Monte Carlo (MCMC), and can be applied to all variables in parallel. As an explainable anomaly detection tool, our changepoint detection method not only triggers alerts, but provides useful information about the structural breaks, such as the times of changepoints, and estimation of mean levels and linear slopes before and after the changepoints. This makes future business analysis and evaluation on the structural breaks easier.

stat.ME↗