arXiv subjects

Qingyun Wu

Publications and source records attributed to Qingyun Wu.

At least 55 records · Page 3Linked to original sources

arXiv2024

Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subset practically performs on par with full data. Practitioners regularly desire to identify the smallest possible coreset in realistic scenes while maintaining comparable model performance, to minimize costs and maximize acceleration. Motivated by this desideratum, for the first time, we pose the problem of refined coreset selection, in which the minimal coreset size under model performance constraints is explored. Moreover, to address this problem, we propose an innovative method, which maintains optimization priority order over the model performance and coreset size, and efficiently optimizes them in the coreset selection procedure. Theoretically, we provide the convergence guarantee of the proposed method. Empirically, extensive experiments confirm its superiority compared with previous strategies, often yielding better model performance with smaller coreset sizes.

cs.LG↗

arXiv2024

Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications

The rapid development in the field of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents to assist humans in their daily tasks. However, a significant gap remains in assessing whether LLM-powered applications genuinely enhance user experience and task execution efficiency. This highlights the pressing need for methods to verify utility of LLM-powered applications, particularly by ensuring alignment between the application's functionality and end-user needs. We introduce AgentEval provides an implementation for the math problems, a novel framework designed to simplify the utility verification process by automatically proposing a set of criteria tailored to the unique purpose of any given application. This allows for a comprehensive assessment, quantifying the utility of an application against the suggested criteria. We present a comprehensive analysis of the robustness of quantifier's work.

cs.CL↗

arXiv2023

Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective

Off-policy Learning to Rank (LTR) aims to optimize a ranker from data collected by a deployed logging policy. However, existing off-policy learning to rank methods often make strong assumptions about how users generate the click data, i.e., the click model, and hence need to tailor their methods specifically under different click models. In this paper, we unified the ranking process under general stochastic click models as a Markov Decision Process (MDP), and the optimal ranking could be learned with offline reinforcement learning (RL) directly. Building upon this, we leverage offline RL techniques for off-policy LTR and propose the Click Model-Agnostic Unified Off-policy Learning to Rank (CUOLR) method, which could be easily applied to a wide range of click models. Through a dedicated formulation of the MDP, we show that offline RL algorithms can adapt to various click models without complex debiasing techniques and prior knowledge of the model. Results on various large-scale datasets demonstrate that CUOLR consistently outperforms the state-of-the-art off-policy learning to rank algorithms while maintaining consistency and robustness under different click models.

cs.LG↗

arXiv2023

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.

cs.AI↗

arXiv2023

Multi-Fidelity Multi-Armed Bandits Revisited

We study the multi-fidelity multi-armed bandit (MF-MAB), an extension of the canonical multi-armed bandit (MAB) problem. MF-MAB allows each arm to be pulled with different costs (fidelities) and observation accuracy. We study both the best arm identification with fixed confidence (BAI) and the regret minimization objectives. For BAI, we present (a) a cost complexity lower bound, (b) an algorithmic framework with two alternative fidelity selection procedures, and (c) both procedures' cost complexity upper bounds. From both cost complexity bounds of MF-MAB, one can recover the standard sample complexity bounds of the classic (single-fidelity) MAB. For regret minimization of MF-MAB, we propose a new regret definition, prove its problem-independent regret lower bound $Ω(K^{1/3}Λ^{2/3})$ and problem-dependent lower bound $Ω(K\log Λ)$, where $K$ is the number of arms and $Λ$ is the decision budget in terms of cost, and devise an elimination-based algorithm whose worst-cost regret upper bound matches its corresponding lower bound up to some logarithmic terms and, whose problem-dependent bound matches its corresponding lower bound in terms of $Λ$.

cs.LG↗

arXiv2023

HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shifts

In this work, we propose a hyperparameter optimization method named \emph{HyperTime} to find hyperparameters robust to potential temporal distribution shifts in the unseen test data. Our work is motivated by an important observation that it is, in many cases, possible to achieve temporally robust predictive performance via hyperparameter optimization. Based on this observation, we leverage the `worst-case-oriented' philosophy from the robust optimization literature to help find such robust hyperparameter configurations. HyperTime imposes a lexicographic priority order on average validation loss and worst-case validation loss over chronological validation sets. We perform a theoretical analysis on the upper bound of the expected test loss, which reveals the unique advantages of our approach. We also demonstrate the strong empirical performance of the proposed method on multiple machine learning tasks with temporal distribution shifts.

cs.LG↗

arXiv2022

FairAutoML: Embracing Unfairness Mitigation in AutoML

In this work, we propose an Automated Machine Learning (AutoML) system to search for models not only with good prediction accuracy but also fair. We first investigate the necessity and impact of unfairness mitigation in the AutoML context. We establish the FairAutoML framework. The framework provides a novel design based on pragmatic abstractions, which makes it convenient to incorporate existing fairness definitions, unfairness mitigation techniques, and hyperparameter search methods into the model search and evaluation process. Following this framework, we develop a fair AutoML system based on an existing AutoML system. The augmented system includes a resource allocation strategy to dynamically decide when and on which models to conduct unfairness mitigation according to the prediction accuracy, fairness, and resource consumption on the fly. Extensive empirical evaluation shows that our system can achieve a good `fair accuracy' and high resource efficiency.

cs.LG↗

arXiv2022

Approaching intrinsic threshold breakdown voltage and ultra-high gain in graphite/InSe Schottky photodetector

Realizing both ultra-low breakdown voltage and ultra-high gain has been one of the major challenges in the development of high-performance avalanche photodetector. Here, we report that an ultra-high avalanche gain of 3*10^5 can be realized in the graphite/InSe Schottky photodetector at a breakdown voltage down to 5.5 V. Remarkably, the threshold breakdown voltage can be further reduced down to 1.8 V by raising the operating temperature, approaching the theoretical limit of 1.5E_g/e with E_g the band gap of semiconductor. We develop a two-dimensional impact ionization model and uncover that observation of high gain at low breakdown voltage arises from reduced dimensionality of electron-phonon (e-ph) scattering in the layered InSe flake. Our findings open up a promising avenue for developing novel weak-light detectors with low energy consumption and high sensitivity.

physics.app-ph↗

arXiv2022

Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users

Static recommendation methods like collaborative filtering suffer from the inherent limitation of performing real-time personalization for cold-start users. Online recommendation, e.g., multi-armed bandit approach, addresses this limitation by interactively exploring user preference online and pursuing the exploration-exploitation (EE) trade-off. However, existing bandit-based methods model recommendation actions homogeneously. Specifically, they only consider the items as the arms, being incapable of handling the item attributes, which naturally provide interpretable information of user's current demands and can effectively filter out undesired items. In this work, we consider the conversational recommendation for cold-start users, where a system can both ask the attributes from and recommend items to a user interactively. This important scenario was studied in a recent work. However, it employs a hand-crafted function to decide when to ask attributes or make recommendations. Such separate modeling of attributes and items makes the effectiveness of the system highly rely on the choice of the hand-crafted function, thus introducing fragility to the system. To address this limitation, we seamlessly unify attributes and items in the same arm space and achieve their EE trade-offs automatically using the framework of Thompson Sampling. Our Conversational Thompson Sampling (ConTS) model holistically solves all questions in conversational recommendation by choosing the arm with the maximal reward to play. Extensive experiments on three benchmark datasets show that ConTS outperforms the state-of-the-art methods Conversational UCB (ConUCB) and Estimation-Action-Reflection model in both metrics of success rate and average number of conversation turns.

cs.IR↗

arXiv2022

Cataloguing MoSi$_2$N$_4$ and WSi$_2$N$_4$ van der Waals Heterostructures: An Exceptional Material Platform for Excitonic Solar Cell Applications

Two-dimensional (2D) materials van der Waals heterostructures (vdWHs) provides a revolutionary route towards high-performance solar energy conversion devices beyond the conventional silicon-based pn junction solar cells. Despite tremendous research progress accomplished in recent years, the searches of vdWHs with exceptional excitonic solar cell conversion efficiency and optical properties remain an open theoretical and experimental quest. Here we show that the vdWH family composed of MoSi$_2$N$_4$ and WSi$_2$N$_4$ monolayers provides a compelling material platform for developing high-performance ultrathin excitonic solar cells and photonics devices. Using first-principle calculations, we construct and classify 51 types of MoSi$_2$N$_4$ and WSi$_2$N$_4$-based [(Mo,W)Si$_2$N$_4$] vdWHs composed of various metallic, semimetallic, semiconducting, insulating and topological 2D materials. Intriguingly, MoSi$_2$N$_4$/(InSe, WSe$_2$) are identified as Type-II vdWHs with exceptional excitonic solar cell power conversion efficiency reaching well over 20%, which are competitive to state-of-art silicon solar cells. The (Mo,W)Si$_2$N$_4$ vdWH family exhibits strong optical absorption in both the visible and ultraviolet regimes. Exceedingly large peak ultraviolet absorptions over 40%, approaching the maximum absorption limit of a free-standing 2D material, can be achieved in (Mo,W)Si$_2$N$_4$/$α_2$-(Mo,W)Ge$_2$P$_4$ vdWHs. Our findings unravel the enormous potential of (Mo,W)Si$_2$N$_4$ vdWHs in designing ultimately compact excitonic solar cell device technology.

cond-mat.mtrl-sci↗

arXiv2022

Provably Efficient Reinforcement Learning for Online Adaptive Influence Maximization

Online influence maximization aims to maximize the influence spread of a content in a social network with unknown network model by selecting a few seed nodes. Recent studies followed a non-adaptive setting, where the seed nodes are selected before the start of the diffusion process and network parameters are updated when the diffusion stops. We consider an adaptive version of content-dependent online influence maximization problem where the seed nodes are sequentially activated based on real-time feedback. In this paper, we formulate the problem as an infinite-horizon discounted MDP under a linear diffusion process and present a model-based reinforcement learning solution. Our algorithm maintains a network model estimate and selects seed users adaptively, exploring the social network while improving the optimal policy optimistically. We establish $\widetilde O(\sqrt{T})$ regret bound for our algorithm. Empirical evaluations on synthetic network demonstrate the efficiency of our algorithm.

cs.LG↗

arXiv2022

Tunable electronic properties and band alignments of MoSi$_2$N$_4$/GaN and MoSi$_2$N$_4$/ZnO van der Waals heterostructures

Van de Waals heterostructures (VDWH) is an emerging strategy to engineer the electronic properties of two-dimensional (2D) material systems. Motivated by the recent discovery of MoSi$_2$N$_4$ - a synthetic septuple-layered 2D semiconductor with exceptional mechanical and electronic properties, we investigate the synergy of \ce{MoSi2N4} with wide band gap (WBG) 2D monolayers of GaN and ZnO using first-principle calculations. We find that MoSi$_2$N$_4$/GaN is a direct band gap Type-I VDWH while MoSi$_2$N$_4$/ZnO is an indirect band gap Type-II VDWH. Intriguingly, by applying an electric field or mechanical strain along the out-of-plane direction, the band structures of MoSi$_2$N$_4$/GaN and MoSi$_2$N$_4$/ZnO can be substantially modified, exhibiting rich transitional behaviors, such as the Type-I-to-Type-II band alignment and the direct-to-indirect band gap transitions. These findings reveal the potentials of MoSi$_2$N$_4$-based WBG VDWH as a tunable hybrid materials with enormous design flexibility in ultracompact optoelectronic applications.

cond-mat.mtrl-sci↗

arXiv2021

ChaCha for Online AutoML

We propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings. ChaCha handles the process of determining a champion and scheduling a set of `live' challengers over time based on sample complexity bounds. It is guaranteed to have sublinear regret after the optimal configuration is added into consideration by an application-dependent oracle based on the champions. Empirically, we show that ChaCha provides good performance across a wide array of datasets when optimizing over featurization and hyperparameter decisions.

cs.LG↗

arXiv2021

FLAML: A Fast and Lightweight AutoML Library

We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data. We investigate the joint impact of multiple factors on both trial cost and model error, and propose several design guidelines. Following them, we build a fast and lightweight library FLAML which optimizes for low computational resource in finding accurate models. FLAML integrates several simple but effective search strategies into an adaptive system. It significantly outperforms top-ranked AutoML libraries on a large open source AutoML benchmark under equal, or sometimes orders of magnitude smaller budget constraints.

cs.LG↗

arXiv2021

When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution

Collaborative bandit learning, i.e., bandit algorithms that utilize collaborative filtering techniques to improve sample efficiency in online interactive recommendation, has attracted much research attention as it enjoys the best of both worlds. However, all existing collaborative bandit learning solutions impose a stationary assumption about the environment, i.e., both user preferences and the dependency among users are assumed static over time. Unfortunately, this assumption hardly holds in practice due to users' ever-changing interests and dependence relations, which inevitably costs a recommender system sub-optimal performance in practice. In this work, we develop a collaborative dynamic bandit solution to handle a changing environment for recommendation. We explicitly model the underlying changes in both user preferences and their dependency relation as a stochastic process. Individual user's preference is modeled by a mixture of globally shared contextual bandit models with a Dirichlet Process prior. Collaboration among users is thus achieved via Bayesian inference over the global bandit models. Model selection and arm selection for each user are done via Thompson sampling to balance exploitation and exploration. Our solution is proved to maintain a standard $\tilde O(\sqrt{T})$ sublinear regret even in such a challenging environment. And extensive empirical evaluations on both synthetic and real-world datasets further confirmed the necessity of modeling a changing environment and our algorithm's practical advantages against several state-of-the-art online learning solutions.

cs.LG↗

arXiv2021

Semiconductor-to-metal transition in bilayer MoSi$_2$N$_4$ and WSi$_2$N$_4$ with strain and electric field

With exceptional electrical and mechanical properties and at the same time air-stability, layered MoSi2N4 has recently draw great attention. However, band structure engineering via strain and electric field, which is vital for practical applications, has not yet been explored. In this work, we show that the biaxial strain and external electric field are effective ways for the band gap engineering of bilayer MoSi$_2$N$_4$ and WSi$_2$N$_4$. It is found that strain can lead to indirect band gap to direct band gap transition. On the other hand, electric field can result in semiconductor to metal transition. Our study provides insights into the band structure engineering of bilayer MoSi$_2$N$_4$ and WSi$_2$N$_4$ and would pave the way for its future nanoelectronics and optoelectronics applications.

cond-mat.mtrl-sci↗

arXiv2020

Frugal Optimization for Cost-related Hyperparameters

The increasing demand for democratizing machine learning algorithms calls for hyperparameter optimization (HPO) solutions at low cost. Many machine learning algorithms have hyperparameters which can cause a large variation in the training cost. But this effect is largely ignored in existing HPO methods, which are incapable to properly control cost during the optimization process. To address this problem, we develop a new cost-frugal HPO solution. The core of our solution is a simple but new randomized direct-search method, for which we prove a convergence rate of $O(\frac{\sqrt{d}}{\sqrt{K}})$ and an $O(dε^{-2})$-approximation guarantee on the total cost. We provide strong empirical results in comparison with state-of-the-art HPO methods on large AutoML benchmarks.

cs.LG↗

arXiv2020

Unifying Clustered and Non-stationary Bandits

Non-stationary bandits and online clustering of bandits lift the restrictive assumptions in contextual bandits and provide solutions to many important real-world scenarios. Though the essence in solving these two problems overlaps considerably, they have been studied independently. In this paper, we connect these two strands of bandit research under the notion of test of homogeneity, which seamlessly addresses change detection for non-stationary bandit and cluster identification for online clustering of bandit in a unified solution framework. Rigorous regret analysis and extensive empirical evaluations demonstrate the value of our proposed solution, especially its flexibility in handling various environment assumptions.

cs.LG↗