3,198 research outputs found
Gu Xiong : The River
No full textGu Xiong’s installation “The River” is described by O’Brian as a meditation on migrancy and displacement. The author situates the work within the life of the artist, who left China because of political oppression, and the history of the Canadian West, which has marginalized its Chinese inhabitants. Short poetic texts by Gu Xiong in which he identifies with spawning salmon are included. Biographical notes. 19 bibl. ref
Visible-light S-scheme heterojunction of copper bismuthate quantum dots decorated Titania-spindles for exceptional tetracycline degradation
No full textThe rational heterojunctions for antibiotics degradation have sparked significant attention in wastewater purification. In this study, we report a unique S-scheme photocatalytic system by in-situ growth of CuBi2O4 quantum dots (QDs) onto {101} facet of TiO2 spindles (TiO2-P) via hydrothermal transformation of Na-titanate nanotubes, which is observed by transmission electron microscopy technology. The CuBi2O4/TiO2-P effectively achieves photo-degradation of tetracycline (TC) using visible light (e.g. an 82% TC degradation efficiency at 60 min), which is attributed to the promotion of the charge separation and retaining strong redox capacity at the heterojunction interfaces via the active species of O-center dot(2)-, (OH)-O-center dot, and h(+). Moreover, density functional theory (DFT) calculations show that a built-in electric field forms at the interface of the S-scheme heterojunction. In all, this work introduces a straightforward in-situ hydrothermal growth method to construct S-scheme photocatalysts for effective water treatment.
Additive manufacturing of high-strength crack-free Ni-based Hastelloy X superalloy
No full textLaser powder bed fusion (LPBF) is a proven additive manufacturing (AM) technology for producing metallic components with complex shapes using layer-by-layer manufacture principle. However, the fabrication of crack-free high-performance Ni-based superalloys such as Hastelloy X (HX) using LPBF technology remains a challenge because of these materials’ susceptibility to hot cracking. This paper addresses the above problem by proposing a novel method of introducing 1 wt.% titanium carbide (TiC) nanoparticles. The findings reveal that the addition of TiC nanoparticles results in the elimination of microcracks in the LPBF-fabricated enhanced HX samples; i.e. the 0.65% microcracks that were formed in the as-fabricated original HX were eliminated in the as-fabricated enhanced HX, despite the 0.14% residual pores formed. It also contributes to a 21.8% increase in low-angle grain boundaries (LAGBs) and a 98 MPa increase in yield strength. The study revealed that segregated carbides were unable to trigger hot cracking without sufficient thermal residual stresses; the significantly increased subgrains and low-angle grain boundaries played a key role in the hot cracking elimination. These findings offer a new perspective on the elimination of hot cracking of nickel-based superalloys and other industrially relevant crack-susceptible alloys. The findings also have significant implications for the design of new alloys, particularly for high-temperature industrial applications
Recommended from our members
Minimax Optimization for Games and for Fine-Tuning of Language Models
No full textThis thesis advances the field of convex-concave minimax optimization by introducing novelalgorithms that outperform traditional methods in various stochastic optimization settings, including
separable strongly convex-strongly concave (SC-SC), bilinearly coupled strongly convex-strongly
concave (bi-SC-SC), bilinear games, etc. Notably, we propose the Accelerated Gradient-Optimistic
Gradient (AG-OG) Descent Ascent and the stochastic Accelerated Gradient-Extragradient (AG-EG)
method. Both algorithms achieve optimal convergence rates in separable minimax optimization and
strongly monotone variational inequalities, respectively, with lower-bound matching convergence
rates specifically in the bilinear game setting. Furthermore, we explore the application of minimax
optimization to enhance large language model fine-tuning through a novel self-play mechanism,
demonstrating significant performance improvements across multiple benchmarks. Our contributions
provide powerful tools for both theoretical research and practical applications in AI and ML,
pushing the boundaries of optimization techniques in these fields
Recommended from our members
Sample-Efficient Nonconvex Optimization Algorithms in Machine Learning and Reinforcement Learning
No full textMachine learning and reinforcement learning have achieved tremendous success in solving problems in various real-world applications. Many modern learning problems boil down to a nonconvex optimization problem, where the objective function is the average or the expectation of some loss function over a finite or infinite dataset. Solving such nonconvex optimization problems, in general, can be NP-hard. Thus one often tackles such a problem through incremental steps based on the nature and the goal of the problem: finding a first-order stationary point, finding a second-order stationary point (or a local optimum), and finding a global optimum. With the size and complexity of the machine learning datasets rapidly increasing, it has become a fundamental challenge to design efficient and scalable machine learning algorithms that can improve the performance in terms of accuracy and save computational cost in terms of sample efficiency at the same time. Though many algorithms based on stochastic gradient descent have been developed and widely studied theoretically and empirically for nonconvex optimization, it has remained an open problem whether we can achieve the optimal sample complexity for finding a first-order stationary point and for finding local optima in nonconvex optimization.
In this thesis, we start with the stochastic nested variance reduced gradient (SNVRG) algorithm, which is developed based on stochastic gradient descent methods and variance reduction techniques. We prove that SNVRG achieves the near-optimal convergence rate among its type for finding a first-order stationary point of a nonconvex function. We further build algorithms to efficiently find the local optimum of a nonconvex objective function by examining the curvature information at the stationary point found by SNVRG. With the ultimate goal of finding the global optimum in nonconvex optimization, we then provide a unified framework to analyze the global convergence of stochastic gradient Langevin dynamics-based algorithms for a nonconvex objective function. In the second part of this thesis, we generalize the aforementioned sample-efficient stochastic nonconvex optimization methods to reinforcement learning problems, including policy gradient, actor-critic, and Q-learning. For these problems, we propose novel algorithms and prove that they enjoy state-of-the-art theoretical guarantees on the sample complexity. The works presented in this thesis form an incomplete collection of the recent advances and developments of sample-efficient nonconvex optimization algorithms for both machine learning and reinforcement learning
Recommended from our members
Evaluating and Understanding Adversarial Robustness in Deep Learning
No full textDeep Neural Networks (DNNs) have made many breakthroughs in different areas of artificial intelligence. However, recent studies show that DNNs are vulnerable to adversarial examples. A tiny perturbation on an image that is almost invisible to human eyes could mislead a well-trained image classifier towards misclassification. This raises serious security concerns and trustworthy issues towards the robustness of Deep Neural Networks in solving real world challenges. Researchers have been working on this problem for a while and it has further led to a vigorous arms race between heuristic defenses that propose ways to defend against existing attacks and newly-devised attacks that are able to penetrate such defenses. While the arm race continues, it becomes more and more crucial to accurately evaluate model robustness effectively and efficiently under different threat models and identify those ``falsely'' robust models that may give us a false sense of robustness. On the other hand, despite the fast development of various kinds of heuristic defenses, their practical robustness is still far from satisfactory, and there are actually little algorithmic improvements in terms of defenses during recent years. This suggests that there still lacks further understandings toward the fundamentals of adversarial robustness in deep learning, which might prevent us from designing more powerful defenses. \\The overarching goal of this research is to enable accurate evaluations of model robustness under different practical settings as well as to establish a deeper understanding towards other factors in the machine learning training pipeline that might affect model robustness. Specifically, we develop efficient and effective Frank-Wolfe attack algorithms under white-box and black-box settings and a hard-label adversarial attack, RayS, which is capable of detecting ``falsely'' robust models. In terms of understanding adversarial robustness, we propose to theoretically study the relationship between model robustness and data distributions, the relationship between model robustness and model architectures, as well as the relationship between model robustness and loss smoothness. The techniques proposed in this dissertation form a line of researches that deepens our understandings towards adversarial robustness and could further guide us in designing better and faster robust training methods
Recommended from our members
Efficient Reinforcement Learning through Uncertainties
No full textThis dissertation is centered around the concept of uncertainty-aware reinforcement learning (RL), which seeks to enhance the efficiency of RL by incorporating uncertainty. RL is a vital mathematical framework in the field of artificial intelligence (AI) for creating autonomous agents that can learn optimal behaviors through interaction with their environments. However, RL is often criticized for being sample inefficient and computationally demanding. To tackle these challenges, the primary goals of this dissertation are twofold: to offer theoretical understanding of uncertainty-aware RL and to develop practical algorithms that utilize uncertainty to enhance the efficiency of RL.Our first objective is to develop an RL approach that is efficient in terms of sample usage for Markov Decision Processes (MDPs) with large state and action spaces. We present an uncertainty-aware RL algorithm that incorporates function approximation. We provide theoretical proof that this algorithm achieves near minimax optimal statistical complexity when learning the optimal policy. In our second objective, we address two specific scenarios: the batch learning setting and the rare policy switch setting. For both settings, we propose uncertainty-aware RL algorithms with limited adaptivity. These algorithms significantly reduce the number of policy switches compared to previous baseline algorithms while maintaining a similar level of statistical complexity. Lastly, we focus on estimating uncertainties in neural network-based estimation models. We introduce a gradient-based method that effectively computes these uncertainties. Our approach is computationally efficient, and the resulting uncertainty estimates are both valid and reliable.The methods and techniques presented in this dissertation contribute to the advancement of our understanding regarding the fundamental limits of RL. These research findings pave the way for further exploration and development in the field of decision-making algorithm design
Recommended from our members
Uncertainty-Aware Unsupervised and Robust Reinforcement Learning
No full textThis dissertation is centered around addressing several key concerns in reinforcement learning (RL). RL has been a popular topic in the design of autonomous intelligent agents that make decisions and learn optimal actions through interaction with the environment. Over the past decades, RL has achieved significant success in various domains. However, RL has consistently been criticized for its inefficiency in exploration and vulnerability to model errors or noise. This dissertation aims to tackle these challenges through uncertainty-aware methods.In the first part of this dissertation, we explore how an RL agent can efficiently explore the environment without human supervision. We begin with a theoretical framework on reward-free exploration and establish a connection between reward-free exploration and unsupervised reinforcement learning. We provide both theoretical analyses and practical algorithms that exhibit competitive empirical performance. In the second part of this dissertation, we aim to develop robust RL algorithm in a misspecified setting, where the function class (e.g., Neural Networks) cannot adequately approximate the underlying ground truth function. We show how significant does approximation error need to be in order to prevent the agent from efficiently learning the environment and making good decisions. We also present several algorithms that ensure the agent will only make a finite number of mistakes over infinite runs when this approximation error is small.The methods and techniques discussed in this dissertation advance the theoretical understanding of key concerns and limitations in RL, particularly in scenarios that require performance guarantees. Additionally, these findings not only suggest further research directions but also pose several open questions that would help better design more robust and efficient decision making processes in the future
Recommended from our members
On the Distance from Calibration in Sequential Prediction
No full textWe study a sequential binary prediction setting where the forecaster is evaluated in terms of the calibration distance, which is defined as the L1 distance between the predicted values and the set of predictions that are perfectly calibrated in hindsight. This is analogous to a calibration measure recently proposed by Błasiok, Gopalan, Hu and Nakkiran (STOC 2023) for the offline setting. The calibration distance is a natural and intuitive measure of deviation from perfect calibration, and satisfies a Lipschitz continuity property which does not hold for many popular calibration measures, such as the L1 calibration error and its variants. We prove that there is a forecasting algorithm that achieves an O(√T) calibration distance in expectation on an adversarially chosen sequence of T binary outcomes. At the core of this upper bound is a structural result showing that the calibration distance is accurately approximated by the lower calibration distance, which is a continuous relaxation of the former. We then show that an O(√T) lower calibration distance can be achieved via a simple minimax argument and a reduction to online learning on a Lipschitz class. On the lower bound side, an Ω(T^(1/3)) calibration distance is shown to be unavoidable, even when the adversary outputs a sequence of independent random bits, and has an additional ability to early stop (i.e., to stop producing random bits and output the same bit in the remaining steps). Interestingly, without this early stopping, the forecaster can achieve a much smaller calibration distance of polylog(T)
Recommended from our members
Towards Efficient and Effective Privacy-Preserving Machine Learning
No full textThe past decade has witnessed the fast growth and tremendous success of machine learning. However, recent studies showed that existing machine learning models are vulnerable to privacy attacks, such as membership inference attacks, and thus pose severe threats to personal privacy. Therefore, one of the major challenges in machine learning is to learn effectively from enormous amounts of sensitive data without giving up on privacy. This dissertation summarizes our contributions to the field of privacy-preserving machine learning, i.e., solving machine learning problems with strong privacy and utility guarantees.In the first part of the dissertation, we consider the privacy-preserving sparse learning problem. More specifically, we establish a novel differentially private hard-thresholding method as well as a knowledge-transfer framework for solving the sparse learning problem. We show that our proposed methods are not only efficient but can also achieve improved privacy and utility guarantees.In the second part of the dissertation, we propose novel efficient and effective algorithms for solving empirical risk minimization problems. To be more specific, our proposed algorithms can reduce the computational complexities and improve the utility guarantees for solving nonconvex optimization problems such as training deep neural networks. In the last part of the dissertation, we study the privacy-preserving empirical risk minimization in the distributed setting. In such a setting, we propose a new privacy-preserving framework by combining the multi-party computation (MPC) protocol and differentially private mechanisms and show that our framework can achieve better privacy and utility guarantees compared with existing methods.The methods and techniques proposed in this dissertation form a line of researches that deepens our understandings of the trade-off between privacy, utility and efficient in privacy-preserving machine learning, and
could also help us develop more efficient and effective private learning algorithms
- …
