arXiv subjects

Dang Nguyen

Publications and source records attributed to Dang Nguyen.

67 records · Page 4Linked to original sources

arXiv2022

Black-box Few-shot Knowledge Distillation

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher (parameters are accessible) to train a good student. However, these resources are not always available in real-world applications. The distillation process often happens at an external party side where we do not have access to much data, and the teacher does not disclose its parameters due to security and privacy concerns. To overcome these challenges, we propose a black-box few-shot KD method to train the student with few unlabeled training samples and a black-box teacher. Our main idea is to expand the training set by generating a diverse set of out-of-distribution synthetic images using MixUp and a conditional variational auto-encoder. These synthetic images along with their labels obtained from the teacher are used to train the student. We conduct extensive experiments to show that our method significantly outperforms recent SOTA few/zero-shot KD methods on image classification tasks. The code and models are available at: https://github.com/nphdang/FS-BBT

cs.CV↗

arXiv2022

On Transportation of Mini-batches: A Hierarchical Approach

Mini-batch optimal transport (m-OT) has been successfully used in practical applications that involve probability measures with a very high number of supports. The m-OT solves several smaller optimal transport problems and then returns the average of their costs and transportation plans. Despite its scalability advantage, the m-OT does not consider the relationship between mini-batches which leads to undesirable estimation. Moreover, the m-OT does not approximate a proper metric between probability measures since the identity property is not satisfied. To address these problems, we propose a novel mini-batch scheme for optimal transport, named Batch of Mini-batches Optimal Transport (BoMb-OT), that finds the optimal coupling between mini-batches and it can be seen as an approximation to a well-defined distance on the space of probability measures. Furthermore, we show that the m-OT is a limit of the entropic regularized version of the BoMb-OT when the regularized parameter goes to infinity. Finally, we carry out experiments on various applications including deep generative models, deep domain adaptation, approximate Bayesian computation, color transfer, and gradient flow to show that the BoMb-OT can be widely applied and performs well in various applications.

stat.ML↗

arXiv2022

Improving Mini-batch Optimal Transport via Partial Transportation

Mini-batch optimal transport (m-OT) has been widely used recently to deal with the memory issue of OT in large-scale applications. Despite their practicality, m-OT suffers from misspecified mappings, namely, mappings that are optimal on the mini-batch level but are partially wrong in the comparison with the optimal transportation plan between the original measures. Motivated by the misspecified mappings issue, we propose a novel mini-batch method by using partial optimal transport (POT) between mini-batch empirical measures, which we refer to as mini-batch partial optimal transport (m-POT). Leveraging the insight from the partial transportation, we explain the source of misspecified mappings from the m-OT and motivate why limiting the amount of transported masses among mini-batches via POT can alleviate the incorrect mappings. Finally, we carry out extensive experiments on various applications such as deep domain adaptation, partial domain adaptation, deep generative model, color transfer, and gradient flow to demonstrate the favorable performance of m-POT compared to current mini-batch methods.

stat.ML↗

arXiv2022

Fast Conditional Network Compression Using Bayesian HyperNetworks

We introduce a conditional compression problem and propose a fast framework for tackling it. The problem is how to quickly compress a pretrained large neural network into optimal smaller networks given target contexts, e.g. a context involving only a subset of classes or a context where only limited compute resource is available. To solve this, we propose an efficient Bayesian framework to compress a given large network into much smaller size tailored to meet each contextual requirement. We employ a hypernetwork to parameterize the posterior distribution of weights given conditional inputs and minimize a variational objective of this Bayesian neural network. To further reduce the network sizes, we propose a new input-output group sparsity factorization of weights to encourage more sparseness in the generated weights. Our methods can quickly generate compressed networks with significantly smaller sizes than baseline methods.

cs.LG↗

arXiv2021

Random switching in an ecosystem with two prey and one predator

In this paper we study the long term dynamics of two prey species and one predator species. In the deterministic setting, if we assume the interactions are of Lotka-Volterra type (competition or predation), the long term behavior of this system is well known. However, nature is usually not deterministic. All ecosystems experience some type of random environmental fluctuations. We incorporate these into a natural framework as follows. Suppose the environment has two possible states. In each of the two environmental states the dynamics is governed by a system of Lotka-Volterra ODE. The randomness comes from spending an exponential amount of time in each environmental state and then switching to the other one. We show how this random switching can create very interesting phenomena. In some cases the randomness can facilitate the coexistence of the three species even though coexistence is impossible in each of the two environmental states. In other cases, even though there is coexistence in each of the two environmental states, switching can lead to the loss of one or more species. We look into how predators and environmental fluctuations can mediate coexistence among competing species.

math.PR↗

arXiv2021

Maximum Likelihood Estimation of Diffusions by Continuous Time Markov Chain

In this paper we present a novel method for estimating the parameters of a parametric diffusion processes. Our approach is based on a closed-form Maximum Likelihood estimator for an approximating Continuous Time Markov Chain (CTMC) of the diffusion process. Unlike typical time discretization approaches, such as psuedo-likelihood approximations with Shoji-Ozaki or Kessler's method, the CTMC approximation introduces no time-discretization error during parameter estimation, and is thus well-suited for typical econometric situations with infrequently sampled data. Due to the structure of the CTMC, we are able to obtain closed-form approximations for the sample likelihood which hold for general univariate diffusions. Comparisons of the state-discretization approach with approximate MLE (time-discretization) and Exact MLE (when applicable) demonstrate favorable performance of the CMTC estimator. Simulated examples are provided in addition to real data experiments with FX rates and constant maturity interest rates.

stat.ME↗

arXiv2021

Stability and Stabilization of Coupled Jump Diffusions and Applications

This paper develops stability and stabilization results for systems of fully coupled jump diffusions. Such systems frequently arise in numerous applications where each subsystem (component) is operated under the influence of other subsystems (components). This paper derives sufficient conditions under which the underlying coupled jump diffusion is stable. The results are then applied to investigate the stability of linearizable jump diffusions, fast-slow coupled jump diffusions. Moreover, weak stabilization of interacting systems and consensus of leader-following systems are examined.

math.PR↗

arXiv2021

Hub and Spoke Logistics Network Design for Urban Region with Clustering-Based Approach

This study aims to propose effective modeling and approach for designing a logistics network in the urban area in order to offer an efficient flow distribution network as a competitive strategy in the logistics industry where demand is sensitive to both price and time. A multi-stage approach is introduced to select the number of hubs and allocate spokes to the hubs for flow distribution and hubs' location detection. Specifically, a fuzzy clustering model with the objective function is to minimize the approximate transportation cost is employed, in the next phase is to focus on balancing the demand capacity among the hubs with the help of domain experts, afterward, the facility location vehicle routing problems within the network is introduced. To demonstrate the approach's advantages, an experiment was performed on the designed network and its actual transportation cost for the real operational data in which specific to the Ho Chi Minh city infrastructure conditions. Additionally, we show the flexibility of the designed network in the flow distribution and its computational experiments to develop the managerial insights which contribute to the network design decision-making process.

cs.LG↗

arXiv2020

Bayesian Optimization with Missing Inputs

Bayesian optimization (BO) is an efficient method for optimizing expensive black-box functions. In real-world applications, BO often faces a major problem of missing values in inputs. The missing inputs can happen in two cases. First, the historical data for training BO often contain missing values. Second, when performing the function evaluation (e.g. computing alloy strength in a heat treatment process), errors may occur (e.g. a thermostat stops working) leading to an erroneous situation where the function is computed at a random unknown value instead of the suggested value. To deal with this problem, a common approach just simply skips data points where missing values happen. Clearly, this naive method cannot utilize data efficiently and often leads to poor performance. In this paper, we propose a novel BO method to handle missing inputs. We first find a probability distribution of each missing value so that we can impute the missing value by drawing a sample from its distribution. We then develop a new acquisition function based on the well-known Upper Confidence Bound (UCB) acquisition function, which considers the uncertainty of imputed values when suggesting the next point for function evaluation. We conduct comprehensive experiments on both synthetic and real-world applications to show the usefulness of our method.

cs.LG↗

arXiv2020

DeepCoDA: personalized interpretability for compositional health data

Interpretability allows the domain-expert to directly evaluate the model's relevance and reliability, a practice that offers assurance and builds trust. In the healthcare setting, interpretable models should implicate relevant biological mechanisms independent of technical factors like data pre-processing. We define personalized interpretability as a measure of sample-specific feature attribution, and view it as a minimum requirement for a precision health model to justify its conclusions. Some health data, especially those generated by high-throughput sequencing experiments, have nuances that compromise precision health models and their interpretation. These data are compositional, meaning that each feature is conditionally dependent on all other features. We propose the Deep Compositional Data Analysis (DeepCoDA) framework to extend precision health modelling to high-dimensional compositional data, and to provide personalized interpretability through patient-specific weights. Our architecture maintains state-of-the-art performance across 25 real-world data sets, all while producing interpretations that are both personalized and fully coherent for compositional data.

cs.LG↗

arXiv2019

Bayesian Optimization for Categorical and Category-Specific Continuous Inputs

Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that formulates the problem as a multi-armed bandit problem, wherein each category corresponds to an arm with its reward distribution centered around the optimum of the objective function in continuous variables. Our goal is to identify the best arm and the maximizer of the corresponding continuous function simultaneously. Our algorithm uses a Thompson sampling scheme that helps connecting both multi-arm bandit and BO in a unified framework. We extend our method to batch BO to allow parallel optimization when multiple resources are available. We theoretically analyze our method for convergence and prove sub-linear regret bounds. We perform a variety of experiments: optimization of several benchmark functions, hyper-parameter tuning of a neural network, and automatic selection of the best machine learning model along with its optimal hyper-parameters (a.k.a automated machine learning). Comparisons with other methods demonstrate the effectiveness of our proposed method.

cs.LG↗

arXiv2019

Stable Bayesian Optimisation via Direct Stability Quantification

In this paper we consider the problem of finding stable maxima of expensive (to evaluate) functions. We are motivated by the optimisation of physical and industrial processes where, for some input ranges, small and unavoidable variations in inputs lead to unacceptably large variation in outputs. Our approach uses multiple gradient Gaussian Process models to estimate the probability that worst-case output variation for specified input perturbation exceeded the desired maxima, and these probabilities are then used to (a) guide the optimisation process toward solutions satisfying our stability criteria and (b) post-filter results to find the best stable solution. We exhibit our algorithm on synthetic and real-world problems and demonstrate that it is able to effectively find stable maxima.

stat.ML↗

arXiv2016

Control Matching via Discharge Code Sequences

In this paper, we consider the patient similarity matching problem over a cancer cohort of more than 220,000 patients. Our approach first leverages on Word2Vec framework to embed ICD codes into vector-valued representation. We then propose a sequential algorithm for case-control matching on this representation space of diagnosis codes. The novel practice of applying the sequential matching on the vector representation lifted the matching accuracy measured through multiple clinical outcomes. We reported the results on a large-scale dataset to demonstrate the effectiveness of our method. For such a large dataset where most clinical information has been codified, the new method is particularly relevant.

cs.LG↗