arXiv subjects

Chao Tian

Publications and source records attributed to Chao Tian.

At least 55 records · Page 3Linked to original sources

arXiv2023

Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detection

RGB-Thermal (RGB-T) pedestrian detection aims to locate the pedestrians in RGB-T image pairs to exploit the complementation between the two modalities for improving detection robustness in extreme conditions. Most existing algorithms assume that the RGB-T image pairs are well registered, while in the real world they are not aligned ideally due to parallax or different field-of-view of the cameras. The pedestrians in misaligned image pairs may locate at different positions in two images, which results in two challenges: 1) how to achieve inter-modality complementation using spatially misaligned RGB-T pedestrian patches, and 2) how to recognize the unpaired pedestrians at the boundary. To deal with these issues, we propose a new paradigm for unregistered RGB-T pedestrian detection, which predicts two separate pedestrian locations in the RGB and thermal images, respectively. Specifically, we propose a cross-modality proposal-guided feature mining (CPFM) mechanism to extract the two precise fusion features for representing the pedestrian in the two modalities, even if the RGB-T image pair is unaligned. It enables us to effectively exploit the complementation between the two modalities. With the CPFM mechanism, we build a two-stream dense detector; it predicts the two pedestrian locations in the two modalities based on the corresponding fusion feature mined by the CPFM mechanism. Besides, we design a data augmentation method, named Homography, to simulate the discrepancy in scales and views between images. We also investigate two non-maximum suppression (NMS) methods for post-processing. Favorable experimental results demonstrate the effectiveness and robustness of our method in dealing with unregistered pedestrians with different shifts.

cs.CV↗

arXiv2023

Layph: Making Change Propagation Constraint in Incremental Graph Processing by Layering Graph

Real-world graphs are constantly evolving, which demands updates of the previous analysis results to accommodate graph changes. By using the memoized previous computation state, incremental graph computation can reduce unnecessary recomputation. However, a small change may propagate over the whole graph and lead to large-scale iterative computations. To address this problem, we propose Layph, a two-layered graph framework. The upper layer is a skeleton of the graph, which is much smaller than the original graph, and the lower layer has some disjointed subgraphs. Layph limits costly global iterative computations on the original graph to the small graph skeleton and a few subgraphs updated with the input graph changes. In this way, many vertices and edges are not involved in iterative computations, significantly reducing the communication overhead and improving incremental graph processing performance. Our experimental results show that Layph outperforms current state-of-the-art incremental graph systems by 9.08X on average (up to 36.66X) in response time.

cs.DC↗

arXiv2023

Optimization of Cryptocurrency Miners' Participation in Ancillary Service Markets

Proof-of-work computation used in cryptocurrencies has witnessed significant growth in the U.S. and many other regions around the world. One of the most significant bottlenecks for the scalable deployment of such computation is its energy demand. On the other hand, the electric energy system is increasing the need for flexibility for energy balancing and ancillary services due to the intermittent nature of many new energy resources such as wind and solar. In this work, we model the operation of a cryptomining facility with heterogeneous mining devices participating in ancillary services. We propose a general formulation for the cryptominers to maximize their profit by strategically participating in ancillary services and controlling the loss of mining revenue, which requires taking into account the disparity in the efficiency of the mining machines. The optimization formulation is considered for both offline and online scenarios, and optimal algorithms are proposed to solve these problems. As a special case of our problem, we investigate cryptominers' participation in frequency regulation, where the miners benefit from their fast-responding devices and contribute to grid stability. In the second special setting, a risk-aware algorithm is proposed to jointly minimize the cost and the risk of participating in ancillary services with homogeneous mining devices. Simulation results based on real-world Electric Reliability Council of Texas (ERCOT) traces show more than 20\% gain in profit, highlighting the advantage of our proposed algorithms.

eess.SY↗

arXiv2023

Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs

We address the issue of safety in reinforcement learning. We pose the problem in an episodic framework of a constrained Markov decision process. Existing results have shown that it is possible to achieve a reward regret of $\tilde{\mathcal{O}}(\sqrt{K})$ while allowing an $\tilde{\mathcal{O}}(\sqrt{K})$ constraint violation in $K$ episodes. A critical question that arises is whether it is possible to keep the constraint violation even smaller. We show that when a strictly safe policy is known, then one can confine the system to zero constraint violation with arbitrarily high probability while keeping the reward regret of order $\tilde{\mathcal{O}}(\sqrt{K})$. The algorithm which does so employs the principle of optimistic pessimism in the face of uncertainty to achieve safe exploration. When no strictly safe policy is known, though one is known to exist, then it is possible to restrict the system to bounded constraint violation with arbitrarily high probability. This is shown to be realized by a primal-dual algorithm with an optimistic primal estimate and a pessimistic dual update.

cs.LG↗

arXiv2023

A Shannon-Theoretic Approach to the Storage-Retrieval Tradeoff in PIR Systems

We consider the storage-retrieval rate tradeoff in private information retrieval (PIR) systems using a Shannon-theoretic approach. Our focus is mostly on the canonical two-message two-database case, for which a coding scheme based on random codebook generation and the binning technique is proposed. This coding scheme reveals a hidden connection between PIR and the classic multiple description source coding problem. We first show that when the retrieval rate is kept optimal, the proposed non-linear scheme can achieve better performance over any linear scheme. Moreover, a non-trivial storage-retrieval rate tradeoff can be achieved beyond space-sharing between this extreme point and the other optimal extreme point, achieved by the retrieve-everything strategy. We further show that with a method akin to the expurgation technique, one can extract a zero-error PIR code from the random code. Outer bounds are also studied and compared to establish the superiority of the non-linear codes over linear codes.

cs.IT↗

arXiv2022

Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning

We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard constraints (constrained MDP), and max-min trade-off. We propose an Anchor-changing Regularized Natural Policy Gradient (ARNPG) framework, which can systematically incorporate ideas from well-performing first-order methods into the design of policy optimization algorithms for multi-objective MDP problems. Theoretically, the designed algorithms based on the ARNPG framework achieve $\tilde{O}(1/T)$ global convergence with exact gradients. Empirically, the ARNPG-guided algorithms also demonstrate superior performance compared to some existing policy gradient-based approaches in both exact gradients and sample-based scenarios.

cs.LG↗

arXiv2022

Improved Weakly Private Information Retrieval Codes

We study the problem of weakly private information retrieval (W-PIR), where a user wishes to retrieve a desired message from $N$ non-colluding servers in a way that the privacy leakage regarding the desired message's identity is less than or equal to a threshold. We propose a new code construction which significantly improves upon the best known result in the literature, based on the following critical observation. In previous constructions, for the extreme case of minimum download, the retrieval pattern is to download the message directly from $N-1$ servers; however this causes leakage to all these $N-1$ servers, and a better retrieval pattern for this extreme case is to download the message directly from a single server. The proposed code construction allows a natural transition to such a pattern, and for both the maximal leakage metric and the mutual information leakage metric, significant improvements can be obtained. We provide explicit solutions, in contrast to a previous work by Lin et al., where only numerical solutions were obtained.

cs.IT↗

arXiv2022

A New Approach to Compute Information Theoretic Outer Bounds and Its Application to Regenerating Codes

The study of the fundamental limits of information systems is a central theme in information theory. Both the traditional analytical approach and the recently proposed computational approach have significant limitations, where the former is mainly due to its reliance on human ingenuity, and the latter due to its exponential memory and computational complexity. In this work, we propose a new computational approach to tackle the problem with much lower memory and computational requirements, which can naturally utilize certain intuitions, but also can maintain the strong computational advantage of the existing computational approach. A reformulation of the underlying optimization problem is first proposed, which converts the large linear program to a maximin problem. This leads to an iterative solving procedure, which uses the LP dual to carry over learned evidence between iterations. The key in the reformulated problem is the selection of good information inequalities, with which a relaxed LP can be formed. A particularly powerful intuition is a potentially optimal code construction, and we provide a method that directly utilizes it in the new algorithm. As an application, we derive a tighter outer bound for the storage-repair tradeoff for the $(6,5,5)$ regenerating code problem, which involves at least 30 random variables and is impossible to compute with the previously known computational approach.

cs.IT↗

arXiv2022

Approximate Top-$m$ Arm Identification with Heterogeneous Reward Variances

We study the effect of reward variance heterogeneity in the approximate top-$m$ arm identification setting. In this setting, the reward for the $i$-th arm follows a $σ^2_i$-sub-Gaussian distribution, and the agent needs to incorporate this knowledge to minimize the expected number of arm pulls to identify $m$ arms with the largest means within error $ε$ out of the $n$ arms, with probability at least $1-δ$. We show that the worst-case sample complexity of this problem is $$Θ\left( \sum_{i =1}^n \frac{σ_i^2}{ε^2} \ln\frac{1}δ + \sum_{i \in G^{m}} \frac{σ_i^2}{ε^2} \ln(m) + \sum_{j \in G^{l}} \frac{σ_j^2}{ε^2} \text{Ent}(σ^2_{G^{r}}) \right),$$ where $G^{m}, G^{l}, G^{r}$ are certain specific subsets of the overall arm set $\{1, 2, \ldots, n\}$, and $\text{Ent}(\cdot)$ is an entropy-like function which measures the heterogeneity of the variance proxies. The upper bound of the complexity is obtained using a divide-and-conquer style algorithm, while the matching lower bound relies on the study of a dual formulation.

cs.LG↗

arXiv2022

On Top-$k$ Selection from $m$-wise Partial Rankings via Borda Counting

We analyze the performance of the Borda counting algorithm in a non-parametric model. The algorithm needs to utilize probabilistic rankings of the items within $m$-sized subsets to accurately determine which items are the overall top-$k$ items in a total of $n$ items. The Borda counting algorithm simply counts the cumulative scores for each item from these partial ranking observations. This generalizes a previous work of a similar nature by Shah et al. using probabilistic pairwise comparison data. The performance of the Borda counting algorithm critically depends on the associated score separation $Δ_k$ between the $k$-th item and the $(k+1)$-th item. Specifically, we show that if $Δ_k$ is greater than certain value, then the top-$k$ items selected by the algorithm is asymptotically accurate almost surely; if $Δ_k$ is below certain value, then the result will be inaccurate with a constant probability. In the special case of $m=2$, i.e., pairwise comparison, the resultant bound is tighter than that given by Shah et al., leading to a reduced gap between the error probability upper and lower bounds. These results are further extended to the approximate top-$k$ selection setting. Numerical experiments demonstrate the effectiveness and accuracy of the Borda counting algorithm, compared with the spectral MLE-based algorithm, particularly when the data does not necessarily follow an assumed parametric model.

cs.DS↗

arXiv2022

Policy Optimization for Constrained MDPs with Provable Fast Global Convergence

We address the problem of finding the optimal policy of a constrained Markov decision process (CMDP) using a gradient descent-based algorithm. Previous results have shown that a primal-dual approach can achieve an $\mathcal{O}(1/\sqrt{T})$ global convergence rate for both the optimality gap and the constraint violation. We propose a new algorithm called policy mirror descent-primal dual (PMD-PD) algorithm that can provably achieve a faster $\mathcal{O}(\log(T)/T)$ convergence rate for both the optimality gap and the constraint violation. For the primal (policy) update, the PMD-PD algorithm utilizes a modified value function and performs natural policy gradient steps, which is equivalent to a mirror descent step with appropriate regularization. For the dual update, the PMD-PD algorithm uses modified Lagrange multipliers to ensure a faster convergence rate. We also present two extensions of this approach to the settings with zero constraint violation and sample-based estimation. Experimental results demonstrate the faster convergence rate and the better performance of the PMD-PD algorithm compared with existing policy gradient-based algorithms.

cs.LG↗

arXiv2022

Stochastic Chaining and Strengthened Information-Theoretic Generalization Bounds

We propose a new approach to apply the chaining technique in conjunction with information-theoretic measures to bound the generalization error of machine learning algorithms. Different from the deterministic chaining approach based on hierarchical partitions of a metric space, previously proposed by Asadi et al., we propose a stochastic chaining approach, which replaces the hierarchical partitions with an abstracted Markovian model borrowed from successive refinement source coding. This approach has three benefits over deterministic chaining: 1) the metric space is not necessarily bounded, 2) facilitation of subsequent analysis to yield more explicit bound, and 3) further opportunity to optimize the bound by removing the geometric rigidity of the partitions. The proposed approach includes the traditional chaining as a special case, and can therefore also utilize any deterministic chaining construction. We illustrate these benefits using the problem of estimating Gaussian mean and that of phase retrieval. For the former, we derive a bound that provides an order-wise improvement over previous results, and for the latter we provide a stochastic chain that allows optimization over the chaining parameter.

cs.IT↗

arXiv2021

Two-Level Private Information Retrieval

In the conventional robust $T$-colluding private information retrieval (PIR) system, the user needs to retrieve one of the possible messages while keeping the identity of the requested message private from any $T$ colluding servers. Motivated by the possible heterogeneous privacy requirements for different messages, we consider the $(N, T_1:K_1, T_2:K_2)$ two-level PIR system with a total of $K_2$ messages in the system, where $T_1\geq T_2$ and $K_1\leq K_2$. Any one of the $K_1$ messages needs to be retrieved privately against $T_1$ colluding servers, and any one of the full set of $K_2$ messages needs to be retrieved privately against $T_2$ colluding servers. We obtain a lower bound to the capacity by proposing two novel coding schemes, namely the non-uniform successive cancellation scheme and the non-uniform block cancellation scheme. A capacity upper bound is also derived. The gap between the upper bound and the lower bounds is analyzed, and shown to vanish when $T_1=T_2$. Lastly, we show that the upper bound is in general not tight by providing a stronger bound for a special setting.

cs.IT↗

arXiv2021

A Fast PC Algorithm with Reversed-order Pruning and A Parallelization Strategy

The PC algorithm is the state-of-the-art algorithm for causal structure discovery on observational data. It can be computationally expensive in the worst case due to the conditional independence tests are performed in an exhaustive-searching manner. This makes the algorithm computationally intractable when the task contains several hundred or thousand nodes, particularly when the true underlying causal graph is dense. We propose a critical observation that the conditional set rendering two nodes independent is non-unique, and including certain redundant nodes do not sacrifice result accuracy. Based on this finding, the innovations of our work are two-folds. First, we innovate on a reserve order linkage pruning PC algorithm which significantly increases the algorithm's efficiency. Second, we propose a parallel computing strategy for statistical independence tests by leveraging tensor computation, which brings further speedup. We also prove the proposed algorithm does not induce statistical power loss under mild graph and data dimensionality assumptions. Experimental results show that the single-threaded version of the proposed algorithm can achieve a 6-fold speedup compared to the PC algorithm on a dense 95-node graph, and the parallel version can make a 825-fold speed-up. We also provide proof that the proposed algorithm is consistent under the same set of conditions with conventional PC algorithm.

cs.LG↗

arXiv2021

On the Fundamental Limits of Coded Caching Systems with Restricted Demand Types

Caching is a technique to reduce the communication load in peak hours by prefetching contents during off-peak hours. An information-theoretic framework for coded caching was introduced by Maddah-Ali and Niesen in a recent work, where it was shown that significant improvement can be obtained compared to uncoded caching. Considerable efforts have been devoted to identify the precise information-theoretic fundamental limits of the coded caching systems, however the difficulty of this task has also become clear. One of the reasons for this difficulty is that the original coded caching setting allows all possible multiple demand types during delivery, which in fact introduces tension in the coding strategy. In this paper, we seek to develop a better understanding of the fundamental limits of coded caching by investigating systems with certain demand type restrictions. We first consider the canonical three-user three-file system, and show that, contrary to popular beliefs, the worst demand type is not the one in which all three files are requested. Motivated by these findings, we focus on coded caching systems where every file must be requested by at least one user. A novel coding scheme is proposed, which can provide new operating points that are not covered by any previously known schemes.

cs.IT↗

arXiv2021

Private Retrieval, Computing and Learning: Recent Progress and Future Challenges

Most of our lives are conducted in the cyberspace. The human notion of privacy translates into a cyber notion of privacy on many functions that take place in the cyberspace. This article focuses on three such functions: how to privately retrieve information from cyberspace (privacy in information retrieval), how to privately leverage large-scale distributed/parallel processing (privacy in distributed computing), and how to learn/train machine learning models from private data spread across multiple users (privacy in distributed (federated) learning). The article motivates each privacy setting, describes the problem formulation, summarizes breakthrough results in the history of each problem, and gives recent results and discusses some of the major ideas that emerged in each field. In addition, the cross-cutting techniques and interconnections between the three topics are discussed along with a set of open problems and challenges.

cs.CR↗

arXiv2020

Individually Conditional Individual Mutual Information Bound on Generalization Error

We propose a new information-theoretic bound on generalization error based on a combination of the error decomposition technique of Bu et al. and the conditional mutual information (CMI) construction of Steinke and Zakynthinou. In a previous work, Haghifam et al. proposed a different bound combining the two aforementioned techniques, which we refer to as the conditional individual mutual information (CIMI) bound. However, in a simple Gaussian setting, both the CMI and the CIMI bounds are order-wise worse than that by Bu et al.. This observation motivated us to propose the new bound, which overcomes this issue by reducing the conditioning terms in the conditional mutual information. In the process of establishing this bound, a conditional decoupling lemma is established, which also leads to a meaningful dichotomy and comparison among these information-theoretic bounds.

cs.IT↗

arXiv2020

User Manual CAI version-1.0: An Open-Source Toolbox for Computer-Aided Investigation on the Fundamental Limits of Information Systems

We provide an open source toolbox on https://github.com/ct2641/CAI/releases/tag/1.0 to conduct computer-aided investigation on the fundamental limits of information systems. The toolbox relies on either Gurobi or Cplex as the linear program solving engine. The program can read a problem description file, and then fulfill the following tasks: 1) compute a bound for a given linear combination of information measures and provide the value of information measures at the optimal solution; 2) efficiently compute a polytope tradeoff outer bound between two information quantities; 3) produce a proof (as a weighted sum of known information inequalities; and 4) provide the range for information quantities between which the optimal value does not change (sensitivity analysis). This technical report provides an overview of this toolbox, a detailed description of the syntax of the problem description file, and a few example use cases.

cs.IT↗