Search Results for author:
Found 124 papers, 31 papers with code
Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation
To address this issue, we connect this structured output learning problem with the structured modeling framework in sequence transduction field.
Multi-Layer SIS Model with an Infrastructure Network
We develop a layered networked spread model for a susceptible-infected-susceptible (SIS) pathogen-borne disease spreading over a human contact network and an infrastructure network, and refer to it as a layered networked susceptible-infected-water-susceptible (SIWS) model.
SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification
Recently, x-vector has been a successful and popular approach for speaker verification, which employs a time delay neural network (TDNN) and statistics pooling to extract speaker characterizing embedding from variable-length utterances.
GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization
During the training process, the polarization effect will drive a subset of gates to smoothly decrease to exact zero, while other gates gradually stay away from zero by a large margin.
Shifted Chunk Transformer for Spatio-Temporal Representational Learning
Leveraging the recent efficient Transformer design in NLP, this shifted chunk Transformer can learn hierarchical spatio-temporal features from a local tiny patch to a global video clip.
PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
In this setting with multiple and constrained goals, this paper discovers that a probabilistic strategic parameter regime can achieve better value compared to the standard regime of finding a single deterministic parameter.
POSO: Personalized Cold Start Modules for Large-scale Recommender Systems
Moreover, POSO can be further generalized to regular users, inactive users and returning users (+2%-3% on Watch Time), as well as item cold start (+3. 8% on Watch Time).
ChemiRise: a data-driven retrosynthesis engine
We have developed an end-to-end, retrosynthesis system, named ChemiRise, that can propose complete retrosynthesis routes for organic compounds rapidly and reliably.
Hand Image Understanding via Deep Multi-Task Learning
To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks.
MugRep: A Multi-Task Hierarchical Graph Representation Learning Framework for Real Estate Appraisal
Real estate appraisal refers to the process of developing an unbiased opinion for real property's market value, which plays a vital role in decision-making for various players in the marketplace (e. g., real estate agents, appraisers, lenders, and buyers).
BAGUA: Scaling up Distributed Learning with System Relaxations
Recent years have witnessed a growing list of systems for distributed data-parallel training.
RankDetNet: Delving Into Ranking Constraints for Object Detection
To this end, we comprehensively investigate three types of ranking constraints, i. e., global ranking, class-specific ranking and IoU-guided ranking losses.
DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents.
From Distributed Machine Learning to Federated Learning: A Survey
Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks.
Distributed Learning Systems with First-order Methods
Scalable and efficient distributed learning is one of the main driving forces behind the recent rapid advancement of machine learning and artificial intelligence.
Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond
Then, to understand the results of interpretation, we also survey the performance metrics for evaluating interpretation algorithms.
On a Network SIS Epidemic Model with Cooperative and Antagonistic Opinion Dynamics
We propose a mathematical model to study coupled epidemic and opinion dynamics in a network of communities.
Influence of flux limitation on large time behavior in a three-dimensional chemotaxis-Stokes system modeling coral fertilization
In this paper, we consider the following system $$\left\{\begin{array}{ll} n_t+u\cdot\nabla n&=\Delta n-\nabla\cdot(n\mathcal{S}(|\nabla c|^2)\nabla c)-nm,\\ c_t+u\cdot\nabla c&=\Delta c-c+m,\\ m_t+u\cdot\nabla m&=\Delta m-mn,\\ u_t&=\Delta u+\nabla P+(n+m)\nabla\Phi,\qquad \nabla\cdot u=0 \end{array}\right.$$ which models the process of coral fertilization, in a smoothly three-dimensional bounded domain, where $\mathcal{S}$ is a given function fulfilling $$|\mathcal{S}(\sigma)|\leq K_{\mathcal{S}}(1+\sigma)^{-\frac{\theta}{2}},\qquad \sigma\geq 0$$ with some $K_{\mathcal{S}}>0.$ Based on conditional estimates of the quantity $c$ and the gradients thereof, a relatively compressed argument as compared to that proceeding in related precedents shows that if $$\theta>0,$$ then for any initial data with proper regularity an associated initial-boundary problem under no-flux/no-flux/no-flux/Dirichlet boundary conditions admits a unique classical solution which is globally bounded, and which also enjoys the stabilization features in the sense that $$\|n(\cdot, t)-n_{\infty}\|_{L^{\infty}(\Omega)}+\|c(\cdot, t)-m_{\infty}\|_{W^{1,\infty}(\Omega)} +\|m(\cdot, t)-m_{\infty}\|_{W^{1,\infty}(\Omega)}+\|u(\cdot, t)\|_{L^{\infty}(\Omega)}\rightarrow0 \quad\textrm{as}~t\rightarrow \infty$$ with $n_{\infty}:=\frac{1}{|\Omega|}\left\{\int_{\Omega}n_0-\int_{\Omega}m_0\right\}_{+}$ and $m_{\infty}:=\frac{1}{|\Omega|}\left\{\int_{\Omega}m_0-\int_{\Omega}n_0\right\}_{+}.$
Analysis of PDEs
Gossip over Holonomic Graphs
A gossip process is an iterative process in a multi-agent system where only two neighboring agents communicate at each iteration and update their states.
Optimization and Control
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
One of the most effective methods is error-compensated compression, which offers robust convergence speed even under 1-bit compression.
Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments
Unfortunately, methods based on intrinsic rewards often fall short in procedurally-generated environments, where a different environment is generated in each episode so that the agent is not likely to visit the same state more than once.
UMEC: Unified model and embedding compression for efficient recommendation systems
The recommendation system (RS) plays an important role in the content recommendation and retrieval scenarios.
C-Watcher: A Framework for Early Detection of High-Risk Neighborhoods Ahead of COVID-19 Outbreak
Furthermore, to transfer the firsthand knowledge (witted in epicenters) to the target city before local outbreaks, we adopt a novel adversarial encoder framework to learn "city-invariant" representations from the mobility-related features for precise early detection of high-risk neighborhoods, even before any confirmed cases known, in the target city.
Relaxed Peephole Optimization: A Novel Compiler Optimization for Quantum Circuits
In this paper, we propose a novel quantum compiler optimization, named relaxed peephole optimization (RPO) for quantum computers.
Quantum Physics Programming Languages
Federated Bandit: A Gossiping Approach
Motivated by the proposal of federated learning, we aim for a solution with which agents will never share their local observations with a central entity, and will be allowed to only share a private copy of his/her own information with their neighbors.
Short Video-based Advertisements Evaluation System: Self-Organizing Learning Approach
In this paper, we proposed a novel end-to-end self-organizing framework for user behavior prediction.
Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
The trained model could be adjusted among different standard and robust accuracies "for free" at testing time.
Ensemble Chinese End-to-End Spoken Language Understanding for Abnormal Event Detection from audio stream
Previous end-to-end SLU models are primarily used for English environment due to lacking large scale SLU dataset in Chines, and use only one ASR model to extract features from speech.
Themes Informed Audio-visual Correspondence Learning
The applications of short-term user-generated video (UGV), such as Snapchat, and Youtube short-term videos, booms recently, raising lots of multimodal machine learning tasks.
Pose-Guided High-Resolution Appearance Transfer via Progressive Training
We propose a novel pose-guided appearance transfer network for transferring a given reference appearance to a target pose in unprecedented image resolution (1024 * 1024), given respectively an image of the reference and target person.
APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm
Adam is the important optimization algorithm to guarantee efficiency and accuracy for training many important tasks such as BERT and ImageNet.
GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework
Generative adversarial networks (GANs) have gained increasing popularity in various computer vision applications, and recently start to be deployed to resource-constrained mobile devices.
Streaming Probabilistic Deep Tensor Factorization
Our algorithm provides responsive incremental updates for the posterior of the latent factors and NN weights upon receiving new tensor entries, and meanwhile select and inhibit redundant/useless weights.
ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting
Via training with regular SGD on the former but a novel update rule with penalty gradients on the latter, we realize structured sparsity.
On Effective Parallelization of Monte Carlo Tree Search
Second, and more importantly, we demonstrate how the proposed necessary conditions can be adopted to design more effective parallel MCTS algorithms.
Neural Network Activation Quantization with Bitwise Information Bottlenecks
Recent researches on information bottleneck shed new light on the continuous attempts to open the black box of neural signal encoding.
Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity
In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms.
Finite-Sample Analysis of Proximal Gradient TD Algorithms
In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms.
Regularized Off-Policy TD-Learning
We present a novel $l_1$ regularized off-policy convergent TD-learning method (termed RO-TD), which is able to learn sparse representations of value functions with low computational complexity.
Data Poisoning Attacks on Federated Machine Learning
To the end, experimental results on real-world datasets show that federated multi-task learning model is very sensitive to poisoning attacks, when the attackers either directly poison the target nodes or indirectly poison the related nodes by exploiting the communication protocol.
Depth Edge Guided CNNs for Sparse Depth Upsampling
Inspired by the normalized convolution operation, we propose a guided convolutional layer to recover dense depth from sparse and irregular depth image with an depth edge image as guidance.
Stochastic Recursive Momentum for Policy Gradient Methods
In this paper, we propose a novel algorithm named STOchastic Recursive Momentum for Policy Gradient (STORM-PG), which operates a SARAH-type stochastic recursive variance-reduced policy gradient in an exponential moving average fashion.
IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval
Existing methods leverage the attention mechanism to explore such correspondence in a fine-grained manner.
Ranked #5 on
Cross-Modal Retrieval
on Flickr30k
End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines
We show that for reasoning components such as MLN and a specific family of Bayesian networks it is possible to certify the robustness of the whole pipeline even with a large magnitude of perturbation which cannot be certified by existing work.
A novel tree-structured point cloud dataset for skeletonization algorithm evaluation
Since the implicit surface is sufficiently expressive to retain the edges and details of the complex branches model, we use the implicit surface to model the triangular mesh.
Stochastic Recursive Variance Reduction for Efficient Smooth Non-Convex Compositional Optimization
Such a complexity is known to be the best one among IFO complexity results for non-convex stochastic compositional optimization, and is believed to be optimal.
Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent
Stochastic compositional optimization arises in many important machine learning tasks such as reinforcement learning and portfolio management.
LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning
A great challenge in cooperative decentralized multi-agent reinforcement learning (MARL) is generating diversified behaviors for each individual agent when receiving only a team reward.
Hierarchical Prototype Learning for Zero-Shot Recognition
Specifically, HPL is able to obtain discriminability on both seen and unseen class domains by learning visual prototypes respectively under the transductive setting.
ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
In this paper, we take an initial attempt, and propose a generic formulation to provide a systematical solution (named ATZSL) for learning a robust ZSL model.
Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based Approach
A key parameter that all existing compression techniques are sensitive to is the compression ratio (e. g., pruning sparsity, quantization bitwidth) of each layer.
Central Server Free Federated Learning over Single-sided Trust Social Networks
However, in many social network scenarios, centralized federated learning is not applicable (e. g., a central agent or server connecting all users may not exist, or the communication cost to the central server is not affordable).
An Interactive Control Approach to 3D Shape Reconstruction
The ability to accurately reconstruct the 3D facets of a scene is one of the key problems in robotic vision.
Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices.
PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
The key problem in graph node embedding lies in how to define the dependence to neighbors.
Improving Adversarial Robustness via Attention and Adversarial Logit Pairing
Finally, we conduct extensive experiments using a wide range of datasets and the experiment results show that our AT+ALP achieves the state of the art defense performance.
$\texttt{DeepSqueeze}$: Decentralization Meets Error-Compensated Compression
Since the \emph{decentralized} training has been witnessed to be superior to the traditional \emph{centralized} training in the communication restricted scenario, therefore a natural question to ask is "how to apply the error-compensated technology to the decentralized learning to further reduce the communication cost."
A Convergence Result for Regularized Actor-Critic Methods
In this paper, we present a probability one convergence proof, under suitable conditions, of a certain class of actor-critic algorithms for finding approximate solutions to entropy-regularized MDPs using the machinery of stochastic approximation.
A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning
This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors.
DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
For example, under the popular parameter server model for distributed learning, the worker nodes need to send the compressed local gradients to the parameter server, which performs the aggregation.
A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning
This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy.
Optimal Projection Guided Transfer Hashing for Image Retrieval
For most existing learning to hash methods, sufficient training images are required and used to learn precise hashing codes.
SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement
Knowledge graph (KG) refinement mainly aims at KG completion and correction (i. e., error detection).
Model Compression with Adversarial Robustness: A Unified Optimization Framework
Deep model compression has been extensively studied, and state-of-the-art methods can now achieve high compression ratios with minimal accuracy loss.
Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Decentralized Online Learning (online learning in decentralized networks) attracts more and more attention, since it is believed that Decentralized Online Learning can help the data providers cooperatively better solve their online problems without sharing their private data to a third party or other providers.
Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis
For recovering 3D object poses from 2D images, a prevalent method is to pre-train an over-complete dictionary $\mathcal D=\{B_i\}_i^D$ of 3D basis poses.
ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
The energy estimate model allows us to formulate DNN compression as a constrained optimization that minimizes the DNN loss function over the energy constraint.
Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity
Regularized empirical risk minimization problem with linear predictor appears frequently in machine learning.
Distributed Learning of Average Belief Over Networks Using Sequential Observations
This paper addresses the problem of distributed learning of average belief with sequential observations, in which a network of $n>1$ agents aim to reach a consensus on the average value of their beliefs, by exchanging information only with their neighbors.
Stochastic Primal-Dual Method for Empirical Risk Minimization with $\mathcal{O}(1)$ Per-Iteration Complexity
Regularized empirical risk minimization problem with linear predictor appears frequently in machine learning.
Dantzig Selector with an Approximately Optimal Denoising Matrix and its Application to Reinforcement Learning
To make the problem computationally tractable, we propose a novel algorithm, termed as Optimal Denoising Dantzig Selector (ODDS), to approximately estimate the optimal denoising matrix.
Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search
Monte Carlo Tree Search (MCTS) algorithms have achieved great success on many challenging benchmarks (e. g., Computer Go).
Distributed Learning over Unreliable Networks
Most of today's distributed machine learning systems assume {\em reliable networks}: whenever two machines exchange information (e. g., gradients or models), the network should guarantee the delivery of the message.
Revisit Batch Normalization: New Understanding from an Optimization View and a Refinement via Composition Optimization
We show when BN works and when BN does not work by analyzing the optimization problem.
Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space
Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely.
Proximal Online Gradient is Optimum for Dynamic Regret
While the online gradient method has been shown to be optimal for the static regret metric, the optimal algorithm for the dynamic regret remains unknown.
Fully Implicit Online Learning
Regularized online learning is widely used in machine learning applications.
TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.
Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem
In this paper, we consider the convex and non-convex composition problem with the structure $\frac{1}{n}\sum\nolimits_{i = 1}^n {{F_i}( {G( x )} )}$, where $G( x )=\frac{1}{n}\sum\nolimits_{j = 1}^n {{G_j}( x )} $ is the inner function, and $F_i(\cdot)$ is the outer function.
$D^2$: Decentralized Training over Decentralized Data
While training a machine learning model using multiple workers, each of which collects data from its own data source, it would be useful when the data collected from different workers are unique and different.
Ranked #3 on
Multi-view Subspace Clustering
on ORL
Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
In the former, an agent learns a policy over $\mathbb{R}^d$ and in the latter, over a discrete set of actions each of which is parametrized by a continuous parameter.
Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking
Deep Neural Networks (DNNs) are increasingly deployed in highly energy-constrained environments such as autonomous drones and wearable devices while at the same time must operate in real-time.
GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning
Graph embedding is a central problem in social network analysis and many other applications, aiming to learn the vector representation for each node.
Parallel Computation of PDFs on Big Spatial Data Using Spark
We consider big spatial data, which is typically produced in scientific areas such as geological or seismic interpretation.
Learning Simple Thresholded Features with Sparse Support Recovery
The thresholded feature has recently emerged as an extremely efficient, yet rough empirical approximation, of the time-consuming sparse coding inference process.
D$^2$: Decentralized Training over Decentralized Data
While training a machine learning model using multiple workers, each of which collects data from their own data sources, it would be most useful when the data collected from different workers can be {\em unique} and {\em different}.
A Robust AUC Maximization Framework with Simultaneous Outlier Detection and Feature Selection for Positive-Unlabeled Classification
The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a few samples labeled as "positive" together with a large volume of "unlabeled" samples that may contain both positive and negative samples.
AutoML from Service Provider's Perspective: Multi-device, Multi-tenant Model Selection with GP-EI
In this paper, we focus on the AutoML problem from the \emph{service provider's perspective}, motivated by the following practical consideration: When an AutoML service needs to serve {\em multiple users} with {\em multiple devices} at the same time, how can we allocate these devices to users in an efficient way?
Communication Compression for Decentralized Training
In this paper, We explore a natural question: {\em can the combination of both techniques lead to a system that is robust to both bandwidth and latency?}
PARAMETRIZED DEEP Q-NETWORKS LEARNING: PLAYING ONLINE BATTLE ARENA WITH DISCRETE-CONTINUOUS HYBRID ACTION SPACE
Most existing deep reinforcement learning (DRL) frameworks consider action spaces that are either discrete or continuous space.
Variance Reduced methods for Non-convex Composition Optimization
In this paper, we apply the variance-reduced technique to derive two variance reduced algorithms that significantly improve the query complexity if the number of inner component functions is large.
Accelerated Method for Stochastic Composition Optimization with Nonsmooth Regularization
To the best of our knowledge, our method admits the fastest convergence rate for stochastic composition optimization: for strongly convex composition problem, our algorithm is proved to admit linear convergence; for general composition problem, our algorithm significantly improves the state-of-the-art convergence rate from $O(T^{-1/2})$ to $O((n_1+n_2)^{{2}/{3}}T^{-1})$.
Gradient Sparsification for Communication-Efficient Distributed Optimization
Modern large scale machine learning applications require stochastic optimization algorithms to be implemented on distributed computational architectures.
Duality-free Methods for Stochastic Composition Optimization
We consider the composition optimization with two expected-value functions in the form of $\frac{1}{n}\sum\nolimits_{i = 1}^n F_i(\frac{1}{m}\sum\nolimits_{j = 1}^m G_j(x))+R(x)$, { which formulates many important problems in statistical learning and machine learning such as solving Bellman equations in reinforcement learning and nonlinear embedding}.
Asynchronous Decentralized Parallel Stochastic Gradient Descent
Can we design an algorithm that is robust in a heterogeneous environment, while being communication efficient and maintaining the best-possible convergence rate?
Cascaded Region-based Densely Connected Network for Event Detection: A Seismic Application
Because of the fact that some positive events are not correctly annotated, we further formulate the detection problem as a learning-from-noise problem.
Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads
We ask, as a "service provider" that manages a shared cluster of machines among all our users running machine learning workloads, what is the resource allocation strategy that maximizes the global satisfaction of all our users?
ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning
We examine training at reduced precision, both from a theoretical and practical perspective, and ask: is it possible to train models at end-to-end low precision with provable guarantees?
An Interactive Greedy Approach to Group Sparsity in High Dimensions
Sparsity learning with known grouping structure has received considerable attention due to wide modern applications in high-dimensional data analysis.
Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent
On network configurations with low bandwidth or high latency, D-PSGD can be up to one order of magnitude faster than its well-optimized centralized counterparts.
Lifelong Metric Learning
In this paper, we consider lifelong learning problem to mimic "human learning", i. e., endowing a new capability to the learned metric for a new task from new online samples and incorporating previous experiences and knowledge.
Asynchronous Parallel Empirical Variance Guided Algorithms for the Thresholding Bandit Problem
This paper proposes an asynchronous parallel thresholding algorithm and its parameter-free version to improve the efficiency and the applicability.
On The Projection Operator to A Three-view Cardinality Constrained Set
The cardinality constraint is an intrinsic way to restrict the solution structure in many domains, for example, sparse learning, feature selection, and compressed sensing.
Negative-Unlabeled Tensor Factorization for Location Category Inference from Highly Inaccurate Mobility Data
In order to efficiently solve the proposed framework, we propose a parameter-free and scalable optimization algorithm by effectively exploring the sparse and low-rank structure of the tensor.
Asynchronous Parallel Greedy Coordinate Descent
n this paper, we propose and study an Asynchronous parallel Greedy Coordinate Descent (Asy-GCD) algorithm for minimizing a smooth function with bounded constraints.
GaDei: On Scale-up Training As A Service For Deep Learning
By evaluating the NLC workloads, we show that only the conservative hyper-parameter setup (e. g., small mini-batch size and small learning rate) can guarantee acceptable model accuracy for a wide range of customers.
The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning
When applied to linear models together with double sampling, we save up to another 1. 7x in data movement compared with uniform quantization.
Prognostics of Surgical Site Infections using Dynamic Health Data
Since existing prediction models of SSI have quite limited capacity to utilize the evolving clinical data, we develop the corresponding solution to equip these mHealth tools with decision-making capabilities for SSI prediction with a seamless assembly of several machine learning models to tackle the analytic challenges arising from the spatial-temporal data.
Efficient Estimation of Compressible State-Space Models with Application to Calcium Signal Deconvolution
In this paper, we consider linear state-space models with compressible innovations and convergent transition matrices in order to model spatiotemporally sparse transient events.
Infinite-Label Learning with Semantic Output Codes
We develop a new statistical machine learning paradigm, named infinite-label learning, to annotate a data point with more than one relevant labels from a candidate set, which pools both the finite labels observed at training and a potentially infinite number of previously unseen labels.
Accelerating Stochastic Composition Optimization
The ASC-PG is the first proximal gradient method for the stochastic composition problem that can deal with nonsmooth regularization penalty.
On Benefits of Selection Diversity via Bilevel Exclusive Sparsity
In this paper, we proposed a general bilevel exclusive sparsity formulation to pursue the diversity by restricting the overall sparsity and the sparsity in each group.
The Teaching Dimension of Linear Learners
Teaching dimension is a learning theoretic quantity that specifies the minimum training set size to teach a target model to a learner.
Staleness-aware Async-SGD for Distributed Deep Learning
Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks.
Exclusive Sparsity Norm Minimization with Random Groups via Cone Projection
To the best of our knowledge, this is the first time to guarantee such convergence rate for the general exclusive sparsity norm minimization; 2) When the group information is unavailable to define the exclusive sparsity norm, we propose to use the random grouping scheme to construct groups and prove that if the number of groups is appropriately chosen, the nonzeros (true features) would be grouped in the ideal way with high probability.
Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization
Asynchronous parallel implementations of stochastic gradient (SG) have been broadly used in solving deep neural network and received many successes in practice recently.
Exclusive Feature Learning on Arbitrary Structures via \ell_{1,2}-norm
Group lasso is widely used to enforce the structural sparsity, which achieves the sparsity at inter-group level.
Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces
In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to design reliable, convergent, and robust reinforcement learning algorithms (ii) how to guarantee that reinforcement learning satisfies pre-specified "safety" guarantees, and remains in a stable region of the parameter space (iii) how to design "off-policy" temporal difference learning algorithms in a reliable and stable manner, and finally (iv) how to integrate the study of reinforcement learning into the rich theory of stochastic optimization.
Forward-Backward Greedy Algorithms for General Convex Smooth Functions over A Cardinality Constraint
Our new bounds are consistent with the bounds of a special case (least squares) and fills a previously existing theoretical gap for general convex smooth functions; 3) We show that the restricted strong convexity condition is satisfied if the number of independent samples is more than $\bar{k}\log d$ where $\bar{k}$ is the sparsity number and $d$ is the dimension of the variable; 4) We apply FoBa-gdt (with the conditional random field objective) to the sensor selection problem for human indoor activity recognition and our results show that FoBa-gdt outperforms other methods (including the ones based on forward greedy selection and L1-regularization).
An Approximate, Efficient LP Solver for LP Rounding
Many problems in machine learning can be solved by rounding the solution of an appropriate linear program.
Dictionary LASSO: Guaranteed Sparse Recovery under Linear Transformation
Specifically, we show 1) in the noiseless case, if the condition number of $D$ is bounded and the measurement number $n\geq \Omega(s\log(p))$ where $s$ is the sparsity number, then the true solution can be recovered with high probability; and 2) in the noisy case, if the condition number of $D$ is bounded and the measurement increases faster than $s\log(p)$, that is, $s\log(p)=o(n)$, the estimate error converges to zero with probability 1 when $p$ and $s$ go to infinity.
Robust Dequantized Compressive Sensing
We consider the reconstruction problem in compressed sensing in which the observations are recorded in a finite number of bits.
Multi-Stage Dantzig Selector
We show that if $X$ obeys a certain condition, then with a large probability the difference between the solution $\hat\beta$ estimated by the proposed method and the true solution $\beta^*$ measured in terms of the $l_p$ norm ($p\geq 1$) is bounded as \begin{equation*} \|\hat\beta-\beta^*\|_p\leq \left(C(s-N)^{1/p}\sqrt{\log m}+\Delta\right)\sigma, \end{equation*} $C$ is a constant, $s$ is the number of nonzero entries in $\beta^*$, $\Delta$ is independent of $m$ and is much smaller than the first term, and $N$ is the number of entries of $\beta^*$ larger than a certain value in the order of $\mathcal{O}(\sigma\sqrt{\log m})$.