arXiv subjects

Bin Yu

Publications and source records attributed to Bin Yu.

At least 109 records · Page 6Linked to original sources

arXiv2023

Bridging Discrete and Backpropagation: Straight-Through and Beyond

Backpropagation, the cornerstone of deep learning, is limited to computing gradients for continuous variables. This limitation poses challenges for problems involving discrete latent variables. To address this issue, we propose a novel approach to approximate the gradient of parameters involved in generating discrete latent variables. First, we examine the widely used Straight-Through (ST) heuristic and demonstrate that it works as a first-order approximation of the gradient. Guided by our findings, we propose ReinMax, which achieves second-order accuracy by integrating Heun's method, a second-order numerical method for solving ODEs. ReinMax does not require Hessian or other second-order derivatives, thus having negligible computation overheads. Extensive experimental results on various tasks demonstrate the superiority of ReinMax over the state of the art. Implementations are released at https://github.com/microsoft/ReinMax.

cs.LG↗

arXiv2023

Revisiting minimum description length complexity in overparameterized models

Complexity is a fundamental concept underlying statistical learning theory that aims to inform generalization performance. Parameter count, while successful in low-dimensional settings, is not well-justified for overparameterized settings when the number of parameters is more than the number of training samples. We revisit complexity measures based on Rissanen's principle of minimum description length (MDL) and define a novel MDL-based complexity (MDL-COMP) that remains valid for overparameterized models. MDL-COMP is defined via an optimality criterion over the encodings induced by a good Ridge estimator class. We provide an extensive theoretical characterization of MDL-COMP for linear models and kernel methods and show that it is not just a function of parameter count, but rather a function of the singular values of the design or the kernel matrix and the signal-to-noise ratio. For a linear model with $n$ observations, $d$ parameters, and i.i.d. Gaussian predictors, MDL-COMP scales linearly with $d$ when $d n$. For kernel methods, we show that MDL-COMP informs minimax in-sample error, and can decrease as the dimensionality of the input increases. We also prove that MDL-COMP upper bounds the in-sample mean squared error (MSE). Via an array of simulations and real-data experiments, we show that a data-driven Prac-MDL-COMP informs hyper-parameter tuning for optimizing test MSE with ridge regression in limited data settings, sometimes improving upon cross-validation and (always) saving computational costs. Finally, our findings also suggest that the recently observed double decent phenomenons in overparameterized models might be a consequence of the choice of non-ideal estimators.

cs.LG↗

arXiv2023

Proton-mediated reversible switching of metastable ferroelectric phases with low operation voltages

The exploration of ferroelectric phase transitions enables an in-depth understanding of ferroelectric switching and promising applications in information storage. However, controllably tuning the dynamics of ferroelectric phase transitions remains challenging owing to inaccessible hidden phases. Here, using protonic gating technology, we create a series of metastable ferroelectric phases and demonstrate their reversible transitions in van der Waals ferroelectric α-In2Se3 transistors. By varying the gate bias, protons can be incrementally injected or extracted, achieving controllable tuning of the ferroelectric α-In2Se3 protonic dynamics across the channel and obtaining numerous intermediate phases. Combining piezoelectric force microscopy and electrical hysteresis measurements, we surprisingly discover that the gate tuning of α-In2Se3 protonation is volatile, unlike the conventional gating effect, and the created new phases remain polar. Their origin, revealed by first-principles calculations, is related to the formation of metastable hydrogen-stabilized α-In2Se3 phases with switchable dipoles. Furthermore, our approach enables ultralow gate-voltage switching of different phases (below 0.4 V), and easy integration with transistor components. This work provides fundamental insights into the interactions between protons and ferroelectric phase transitions, providing a possible avenue for accessing hidden phases in ferroelectric switching and for developing energy-efficient, multilevel-switching memory devices.

cond-mat.mtrl-sci↗

arXiv2023

TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Models

With the promotion of chatgpt to the public, Large language models indeed showcase remarkable common sense, reasoning, and planning skills, frequently providing insightful guidance. These capabilities hold significant promise for their application in urban traffic management and control. However, LLMs struggle with addressing traffic issues, especially processing numerical data and interacting with simulations, limiting their potential in solving traffic-related challenges. In parallel, specialized traffic foundation models exist but are typically designed for specific tasks with limited input-output interactions. Combining these models with LLMs presents an opportunity to enhance their capacity for tackling complex traffic-related problems and providing insightful suggestions. To bridge this gap, we present TrafficGPT, a fusion of ChatGPT and traffic foundation models. This integration yields the following key enhancements: 1) empowering ChatGPT with the capacity to view, analyze, process traffic data, and provide insightful decision support for urban transportation system management; 2) facilitating the intelligent deconstruction of broad and complex tasks and sequential utilization of traffic foundation models for their gradual completion; 3) aiding human decision-making in traffic control through natural language dialogues; and 4) enabling interactive feedback and solicitation of revised outcomes. By seamlessly intertwining large language model and traffic expertise, TrafficGPT not only advances traffic management but also offers a novel approach to leveraging AI capabilities in this domain. The TrafficGPT demo can be found in https://github.com/lijlansg/TrafficGPT.git.

cs.AI↗

arXiv2023

The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning

In this work, we investigate the dynamics of stochastic gradient descent (SGD) when training a single-neuron autoencoder with linear or ReLU activation on orthogonal data. We show that for this non-convex problem, randomly initialized SGD with a constant step size successfully finds a global minimum for any batch size choice. However, the particular global minimum found depends upon the batch size. In the full-batch setting, we show that the solution is dense (i.e., not sparse) and is highly aligned with its initialized direction, showing that relatively little feature learning occurs. On the other hand, for any batch size strictly smaller than the number of samples, SGD finds a global minimum which is sparse and nearly orthogonal to its initialization, showing that the randomness of stochastic gradients induces a qualitatively different type of "feature selection" in this setting. Moreover, if we measure the sharpness of the minimum by the trace of the Hessian, the minima found with full batch gradient descent are flatter than those found with strictly smaller batch sizes, in contrast to previous works which suggest that large batches lead to sharper minima. To prove convergence of SGD with a constant step size, we introduce a powerful tool from the theory of non-homogeneous random walks which may be of independent interest.

stat.ML↗

arXiv2023

Signed iterative random forests to identify enhancer-associated transcription factor binding

Standard ChIP-seq peak calling pipelines seek to differentiate biochemically reproducible signals of individual genomic elements from background noise. However, reproducibility alone does not imply functional regulation (e.g., enhancer activation, alternative splicing). Here we present a general-purpose, interpretable machine learning method: signed iterative random forests (siRF), which we use to infer regulatory interactions among transcription factors and functional binding signatures surrounding enhancer elements in Drosophila melanogaster.

stat.ML↗

arXiv2023

Fast Interpretable Greedy-Tree Sums

Modern machine learning has achieved impressive prediction performance, but often sacrifices interpretability, a critical consideration in high-stakes domains such as medicine. In such settings, practitioners often use highly interpretable decision tree models, but these suffer from inductive bias against additive structure. To overcome this bias, we propose Fast Interpretable Greedy-Tree Sums (FIGS), which generalizes the CART algorithm to simultaneously grow a flexible number of trees in summation. By combining logical rules with addition, FIGS is able to adapt to additive structure while remaining highly interpretable. Extensive experiments on real-world datasets show that FIGS achieves state-of-the-art prediction performance. To demonstrate the usefulness of FIGS in high-stakes domains, we adapt FIGS to learn clinical decision instruments (CDIs), which are tools for guiding clinical decision-making. Specifically, we introduce a variant of FIGS known as G-FIGS that accounts for the heterogeneity in medical data. G-FIGS derives CDIs that reflect domain knowledge and enjoy improved specificity (by up to 20% over CART) without sacrificing sensitivity or interpretability. To provide further insight into FIGS, we prove that FIGS learns components of additive models, a property we refer to as disentanglement. Further, we show (under oracle conditions) that unconstrained tree-sum models leverage disentanglement to generalize more efficiently than single decision tree models when fitted to additive regression functions. Finally, to avoid overfitting with an unconstrained number of splits, we develop Bagging-FIGS, an ensemble version of FIGS that borrows the variance reduction techniques of random forests. Bagging-FIGS enjoys competitive performance with random forests and XGBoost on real-world datasets.

cs.LG↗

arXiv2023

SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Autoregressive large language models (LLMs) have made remarkable progress in various natural language generation tasks. However, they incur high computation cost and latency resulting from the autoregressive token-by-token generation. To address this issue, several approaches have been proposed to reduce computational cost using early-exit strategies. These strategies enable faster text generation using reduced computation without applying the full computation graph to each token. While existing token-level early exit methods show promising results for online inference, they cannot be readily applied for batch inferencing and Key-Value caching. This is because they have to wait until the last token in a batch exits before they can stop computing. This severely limits the practical application of such techniques. In this paper, we propose a simple and effective token-level early exit method, SkipDecode, designed to work seamlessly with batch inferencing and KV caching. It overcomes prior constraints by setting up a singular exit point for every token in a batch at each sequence position. It also guarantees a monotonic decrease in exit points, thereby eliminating the need to recompute KV Caches for preceding tokens. Rather than terminating computation prematurely as in prior works, our approach bypasses lower to middle layers, devoting most of the computational resources to upper layers, allowing later tokens to benefit from the compute expenditure by earlier tokens. Our experimental results show that SkipDecode can obtain 2x to 5x inference speedups with negligible regression across a variety of tasks. This is achieved using OPT models of 1.3 billion and 6.7 billion parameters, all the while being directly compatible with batching and KV caching optimization techniques.

cs.CL↗

arXiv2023

Estimation of the flux at 1450MHz of OB stars for FAST and SKA

Radio observation is crucial to understanding the wind mechanism of OB stars but very scarce. This work estimates the flux at 1450MHz ($S_{\rm 1.4GHz}$) of about 5,000 OB stars identified by the LAMOST spectroscopic survey and confirmed by the Gaia astrometric as well as astrophysical measurements. The calculation is performed under the free-free emission mechanism for wind with the mass loss rate derived from stellar parameters. The estimated $S_{\rm 1.4GHz}$ distributes from $10^{-11}$Jy to $10^{-3}$Jy with the peak at about $10^{-8}$Jy. This implies that the complete SKA-II can detect more than half of them, and some tens of objects are detectable by FAST without considering source confusion. An array of FAST would increase the detectable sample by two orders of magnitude.

astro-ph.SR↗

arXiv2023

Enhancing Peak Network Traffic Prediction via Time-Series Decomposition

For network administration and maintenance, it is critical to anticipate when networks will receive peak volumes of traffic so that adequate resources can be allocated to service requests made to servers. In the event that sufficient resources are not allocated to servers, they can become prone to failure and security breaches. On the contrary, we would waste a lot of resources if we always allocate the maximum amount of resources. Therefore, anticipating peak volumes in network traffic becomes an important problem. However, popular forecasting models such as Autoregressive Integrated Moving Average (ARIMA) forecast time-series data generally, thus lack in predicting peak volumes in these time-series. More than often, a time-series is a combination of different features, which may include but are not limited to 1) Trend, the general movement of the traffic volume, 2) Seasonality, the patterns repeated over some time periods (e.g. daily and monthly), and 3) Noise, the random changes in the data. Considering that the fluctuation of seasonality can be harmful for trend and peak prediction, we propose to extract seasonalities to facilitate the peak volume predictions in the time domain. The experiments on both synthetic and real network traffic data demonstrate the effectiveness of the proposed method.

cs.NI↗

arXiv2022

A Systems Engineering Approach to Modeling and Analysis of Chronic Obstructive Pulmonary Disease (COPD)

Chronic Obstructive Pulmonary Disease (COPD) is a progressive lung disease characterized by airflow limitation. This study develops a systems engineering framework for representing important mechanistic details of COPD in a model of the cardio-respiratory system. In this model, we present the cardio-respiratory system as an integrated biological control system responsible for regulating breathing. Four engineering control system components are considered: sensor, controller, actuator, and the process itself. Knowledge of human anatomy and physiology is used to develop appropriate mechanistic mathematical models for each component. Following a systematic analysis of the computational model, we identify three physiological parameters associated with reproducing clinical manifestations of COPD - changes in the forced expiratory volume (FEV), lung volumes, and pulmonary hypertension. We quantify the changes in these parameters (airway resistance, lung elastance, and pulmonary resistance) as the ones that result in a systemic response that is diagnostic of COPD. A multivariate analysis reveals that the changes in airway resistance have a broad impact on the human cardio-respiratory system, and that the pulmonary circuit is stressed beyond normal under hypoxic environments in most COPD patients.

physics.med-ph↗

arXiv2022

Charge Crowding in Graphene-Silicon Diodes

The performance of nanoscale electronic devices based on a two-three dimensional (2D-3D) interface is significantly affected by the electrical contacts that interconnect these materials with external circuitry. This work investigates charge transport effects at the 2D-3D ohmic contact coupled with the thermionic injection model for graphene/Si Schottky junction. Here, w e focus on the intrinsic properties of graphene-metal contacts, paying particular attention to the nature of the contact failure mechanism under high electrical stress. According to our findings, severe current crowding (CC) effects in highly conductive electrical contact significantly affect device failure that can be reduced by spatially varying the contact properties and geometry. The impact of electrical breakdown on material degradation is systematically analyzed by atomic force, Raman, scanning electron, and energy dispersive X-ray spectroscopies. Our devices withstand high electrostatic discharge spikes over a longer period, manifesting high robustness and operational stability. This research paves the way towards a highly robust and reliable graphene/Si heterostructure in futuristic on-chip integration in dynamic switching. The methods we employed here can be extended for other nanoscale electronic devices based on 2D-3D interfaces

physics.app-ph↗

arXiv2022

A Mixing Time Lower Bound for a Simplified Version of BART

Bayesian Additive Regression Trees (BART) is a popular Bayesian non-parametric regression algorithm. The posterior is a distribution over sums of decision trees, and predictions are made by averaging approximate samples from the posterior. The combination of strong predictive performance and the ability to provide uncertainty measures has led BART to be commonly used in the social sciences, biostatistics, and causal inference. BART uses Markov Chain Monte Carlo (MCMC) to obtain approximate posterior samples over a parameterized space of sums of trees, but it has often been observed that the chains are slow to mix. In this paper, we provide the first lower bound on the mixing time for a simplified version of BART in which we reduce the sum to a single tree and use a subset of the possible moves for the MCMC proposal distribution. Our lower bound for the mixing time grows exponentially with the number of data points. Inspired by this new connection between the mixing time and the number of data points, we perform rigorous simulations on BART. We show qualitatively that BART's mixing time increases with the number of data points. The slow mixing time of the simplified BART suggests a large variation between different runs of the simplified BART algorithm and a similar large variation is known for BART in the literature. This large variation could result in a lack of stability in the models, predictions, and posterior intervals obtained from the BART MCMC samples. Our lower bound and simulations suggest increasing the number of chains with the number of data points.

stat.ML↗

arXiv2022

Same Root Different Leaves: Time Series and Cross-Sectional Methods in Panel Data

A central goal in social science is to evaluate the causal effect of a policy. One dominant approach is through panel data analysis in which the behaviors of multiple units are observed over time. The information across time and space motivates two general approaches: (i) horizontal regression (i.e., unconfoundedness), which exploits time series patterns, and (ii) vertical regression (e.g., synthetic controls), which exploits cross-sectional patterns. Conventional wisdom states that the two approaches are fundamentally different. We establish this position to be partly false for estimation but generally true for inference. In particular, we prove that both approaches yield identical point estimates under several standard settings. For the same point estimate, however, each approach quantifies uncertainty with respect to a distinct estimand. In turn, the confidence interval developed for one estimand may have incorrect coverage for another. This emphasizes that the source of randomness that researchers assume has direct implications for the accuracy of inference.

econ.EM↗

arXiv2022

SOFFLFM: Super-resolution optical fluctuation Fourier light-field microscopy

Fourier light-field microscopy (FLFM) uses a micro-lens array (MLA) to segment the Fourier Plane of the microscopic objective lens to generate multiple two-dimensional perspective views, thereby reconstructing the three-dimensional(3D) structure of the sample using 3D deconvolution calculation without scanning. However, the resolution of FLFM is still limited by diffraction, and furthermore, dependent on the aperture division. In order to improve its resolution, a Super-resolution optical fluctuation Fourier light field microscopy (SOFFLFM) was proposed here, in which the Sofi method with ability of super-resolution was introduced into FLFM. SOFFLFM uses higher-order cumulants statistical analysis on an image sequence collected by FLFM, and then carries out 3D deconvolution calculation to reconstruct the 3D structure of the sample. Theoretical basis of SOFFLFM on improving resolution was explained and then verified with simulations. Simulation results demonstrated that SOFFLFM improved lateral and axial resolution by more than sqrt(2) and 2 times in the 2nd and 4th order accumulations, compared with that of FLFM.

physics.optics↗

arXiv2022

Towards Robust Waveform-Based Acoustic Models

We study the problem of learning robust acoustic models in adverse environments, characterized by a significant mismatch between training and test conditions. This problem is of paramount importance for the deployment of speech recognition systems that need to perform well in unseen environments. First, we characterize data augmentation theoretically as an instance of vicinal risk minimization, which aims at improving risk estimates during training by replacing the delta functions that define the empirical density over the input space with an approximation of the marginal population density in the vicinity of the training samples. More specifically, we assume that local neighborhoods centered at training samples can be approximated using a mixture of Gaussians, and demonstrate theoretically that this can incorporate robust inductive bias into the learning process. We then specify the individual mixture components implicitly via data augmentation schemes, designed to address common sources of spurious correlations in acoustic models. To avoid potential confounding effects on robustness due to information loss, which has been associated with standard feature extraction techniques (e.g., FBANK and MFCC features), we focus on the waveform-based setting. Our empirical results show that the approach can generalize to unseen noise conditions, with 150% relative improvement in out-of-distribution generalization compared to training using the standard risk minimization principle. Moreover, the results demonstrate competitive performance relative to models learned using a training sample designed to match the acoustic conditions characteristic of test utterances.

cs.SD↗

arXiv2022

Learning Using Privileged Information for Zero-Shot Action Recognition

Zero-Shot Action Recognition (ZSAR) aims to recognize video actions that have never been seen during training. Most existing methods assume a shared semantic space between seen and unseen actions and intend to directly learn a mapping from a visual space to the semantic space. This approach has been challenged by the semantic gap between the visual space and semantic space. This paper presents a novel method that uses object semantics as privileged information to narrow the semantic gap and, hence, effectively, assist the learning. In particular, a simple hallucination network is proposed to implicitly extract object semantics during testing without explicitly extracting objects and a cross-attention module is developed to augment visual feature with the object semantics. Experiments on the Olympic Sports, HMDB51 and UCF101 datasets have shown that the proposed method outperforms the state-of-the-art methods by a large margin.

cs.CV↗

arXiv2022

Group Probability-Weighted Tree Sums for Interpretable Modeling of Heterogeneous Data

Machine learning in high-stakes domains, such as healthcare, faces two critical challenges: (1) generalizing to diverse data distributions given limited training data while (2) maintaining interpretability. To address these challenges, we propose an instance-weighted tree-sum method that effectively pools data across diverse groups to output a concise, rule-based model. Given distinct groups of instances in a dataset (e.g., medical patients grouped by age or treatment site), our method first estimates group membership probabilities for each instance. Then, it uses these estimates as instance weights in FIGS (Tan et al. 2022), to grow a set of decision trees whose values sum to the final prediction. We call this new method Group Probability-Weighted Tree Sums (G-FIGS). G-FIGS achieves state-of-the-art prediction performance on important clinical datasets; e.g., holding the level of sensitivity fixed at 92%, G-FIGS increases specificity for identifying cervical spine injury by up to 10% over CART and up to 3% over FIGS alone, with larger gains at higher sensitivity levels. By keeping the total number of rules below 16 in FIGS, the final models remain interpretable, and we find that their rules match medical domain expertise. All code, data, and models are released on Github.

cs.LG↗