arXiv subjects

Yu-Jie Zhang

Publications and source records attributed to Yu-Jie Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2024

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical

Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches have relied on the uniform distribution assumption to model the generation of complementary labels, or on an ordinary-label training set to estimate the transition matrix in non-uniform cases. However, either condition may not be satisfied in real-world scenarios. In this paper, we propose a novel consistent approach that does not rely on these conditions. Inspired by the positive-unlabeled (PU) learning literature, we propose an unbiased risk estimator based on the Selected-Completely-at-Random assumption for complementary-label learning. We then introduce a risk-correction approach to address overfitting problems. Furthermore, we find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems when using the one-versus-rest strategy. Extensive experimental results on both synthetic and real-world benchmark datasets validate the superiority of our proposed approach over state-of-the-art methods.

cs.LG↗

arXiv2024

Exploratory Machine Learning with Unknown Unknowns

In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to known labels. This paper studies a new problem setting in which there are unknown classes in the training data misperceived as other labels, and thus their existence appears unknown from the given supervision. We attribute the unknown unknowns to the fact that the training dataset is badly advised by the incompletely perceived label space due to the insufficient feature information. To this end, we propose the exploratory machine learning, which examines and investigates training data by actively augmenting the feature space to discover potentially hidden classes. Our method consists of three ingredients including rejection model, feature exploration, and model cascade. We provide theoretical analysis to justify its superiority, and validate the effectiveness on both synthetic and real datasets.

cs.LG↗

arXiv2024

Adapting to Continuous Covariate Shift via Online Density Ratio Estimation

Dealing with distribution shifts is one of the central challenges for modern machine learning. One fundamental situation is the covariate shift, where the input distributions of data change from training to testing stages while the input-conditional output distribution remains unchanged. In this paper, we initiate the study of a more challenging scenario -- continuous covariate shift -- in which the test data appear sequentially, and their distributions can shift continuously. Our goal is to adaptively train the predictor such that its prediction risk accumulated over time can be minimized. Starting with the importance-weighted learning, we show the method works effectively if the time-varying density ratios of test and train inputs can be accurately estimated. However, existing density ratio estimation methods would fail due to data scarcity at each time step. To this end, we propose an online method that can appropriately reuse historical information. Our density ratio estimation method is proven to perform well by enjoying a dynamic regret bound, which finally leads to an excess risk guarantee for the predictor. Empirical results also validate the effectiveness.

cs.LG↗

arXiv2024

Novel method for identifying the heaviest QED atom

The bound state of a $τ^+τ^-$ pair by the electromagnetic force is the heaviest and smallest QED atom. Since the discovery of the two lightest QED atoms more than 60 years ago, no evidence for the third one has been found. We demonstrate that the $J_τ$ ($τ^+τ^-$ atom with $J^{PC}=1^{--}$) resonance signal can be observed with a significance larger than $5σ$ including both statistical and systematic uncertainties, via the process $e^+e^-\to X^+ Y^- \slashed{E}$ ($X,\,Y=e$, $μ$, $π$, $K$, or $ρ$, and $\slashed{E}$ is the missing energy) with $1.5~{\rm ab^{-1}}$ data taken around the $τ$ pair production threshold. The $τ$ lepton mass can be measured in a precision of 2 keV with the same data sample. This is within one year's running time of the proposed super tau-charm factory or super charm-tau factory.

hep-ph↗

arXiv2024

Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization

We investigate online convex optimization in non-stationary environments and choose dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible comparator sequence. Let $T$ be the time horizon and $P_T$ be the path length that essentially reflects the non-stationarity of environments, the state-of-the-art dynamic regret is $\mathcal{O}(\sqrt{T(1+P_T)})$. Although this bound is proved to be minimax optimal for convex functions, in this paper, we demonstrate that it is possible to further enhance the guarantee for some easy problem instances, particularly when online functions are smooth. Specifically, we introduce novel online algorithms that can exploit smoothness and replace the dependence on $T$ in dynamic regret with problem-dependent quantities: the variation in gradients of loss functions, the cumulative loss of the comparator sequence, and the minimum of these two terms. These quantities are at most $\mathcal{O}(T)$ while could be much smaller in benign environments. Therefore, our results are adaptive to the intrinsic difficulty of the problem, since the bounds are tighter than existing results for easy problems and meanwhile safeguard the same rate in the worst case. Notably, our proposed algorithms can achieve favorable dynamic regret with only one gradient per iteration, sharing the same gradient query complexity as the static regret minimization methods. To accomplish this, we introduce the collaborative online ensemble framework. The proposed framework employs a two-layer online ensemble to handle non-stationarity, and uses optimistic online learning and further introduces crucial correction terms to enable effective collaboration within the meta-base two layers, thereby attaining adaptivity. We believe the framework can be useful for broader problems.

cs.LG↗

arXiv2024

Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization

Stochastically Extended Adversarial (SEA) model is introduced by Sachs et al. [2022] as an interpolation between stochastic and adversarial online convex optimization. Under the smoothness condition, they demonstrate that the expected regret of optimistic follow-the-regularized-leader (FTRL) depends on the cumulative stochastic variance $σ_{1:T}^2$ and the cumulative adversarial variation $Σ_{1:T}^2$ for convex functions. They also provide a slightly weaker bound based on the maximal stochastic variance $σ_{\max}^2$ and the maximal adversarial variation $Σ_{\max}^2$ for strongly convex functions. Inspired by their work, we investigate the theoretical guarantees of optimistic online mirror descent (OMD) for the SEA model. For convex and smooth functions, we obtain the same $\mathcal{O}(\sqrt{σ_{1:T}^2}+\sqrt{Σ_{1:T}^2})$ regret bound, without the convexity requirement of individual functions. For strongly convex and smooth functions, we establish an $\mathcal{O}((σ_{\max}^2 + Σ_{\max}^2) \log (σ_{1:T}^2+Σ_{1:T}^2))$ bound, better than their $\mathcal{O}((σ_{\max}^2 + Σ_{\max}^2) \log T)$ result. For exp-concave and smooth functions, we achieve a new $\mathcal{O}(d\log(σ_{1:T}^2+Σ_{1:T}^2))$ bound. Owing to the OMD framework, we broaden our work to study dynamic regret minimization and scenarios where the online functions are non-smooth. We establish the first dynamic regret guarantee for the SEA model with convex and smooth functions, which is more favorable than static regret bounds in non-stationary scenarios. Furthermore, to deal with non-smooth and convex functions in the SEA model, we propose novel algorithms building on optimistic OMD with an implicit update, which provably attain static regret and dynamic regret guarantees without smoothness conditions.

cs.LG↗

arXiv2023

Adapting to Online Label Shift with Provable Guarantees

The standard supervised learning paradigm works effectively when training data shares the same distribution as the upcoming testing samples. However, this stationary assumption is often violated in real-world applications, especially when testing data appear in an online fashion. In this paper, we formulate and investigate the problem of \emph{online label shift} (OLaS): the learner trains an initial model from the labeled offline data and then deploys it to an unlabeled online environment where the underlying label distribution changes over time but the label-conditional density does not. The non-stationarity nature and the lack of supervision make the problem challenging to be tackled. To address the difficulty, we construct a new unbiased risk estimator that utilizes the unlabeled data, which exhibits many benign properties albeit with potential non-convexity. Building upon that, we propose novel online ensemble algorithms to deal with the non-stationarity of the environments. Our approach enjoys optimal \emph{dynamic regret}, indicating that the performance is competitive with a clairvoyant who knows the online environments in hindsight and then chooses the best decision for each round. The obtained dynamic regret bound scales with the intensity and pattern of label distribution shift, hence exhibiting the adaptivity in the OLaS problem. Extensive experiments are conducted to validate the effectiveness and support our theoretical findings.

cs.LG↗

arXiv2020

Dynamic Regret of Convex and Smooth Functions

We investigate online convex optimization in non-stationary environments and choose the dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible comparator sequence. Let $T$ be the time horizon and $P_T$ be the path-length that essentially reflects the non-stationarity of environments, the state-of-the-art dynamic regret is $\mathcal{O}(\sqrt{T(1+P_T)})$. Although this bound is proved to be minimax optimal for convex functions, in this paper, we demonstrate that it is possible to further enhance the dynamic regret by exploiting the smoothness condition. Specifically, we propose novel online algorithms that are capable of leveraging smoothness and replace the dependence on $T$ in the dynamic regret by problem-dependent quantities: the variation in gradients of loss functions, the cumulative loss of the comparator sequence, and the minimum of the previous two terms. These quantities are at most $\mathcal{O}(T)$ while could be much smaller in benign environments. Therefore, our results are adaptive to the intrinsic difficulty of the problem, since the bounds are tighter than existing results for easy problems and meanwhile guarantee the same rate in the worst case.

cs.LG↗

arXiv2020

An Unbiased Risk Estimator for Learning with Augmented Classes

This paper studies the problem of learning with augmented classes (LAC), where augmented classes unobserved in the training data might emerge in the testing phase. Previous studies generally attempt to discover augmented classes by exploiting geometric properties, achieving inspiring empirical performance yet lacking theoretical understandings particularly on the generalization ability. In this paper we show that, by using unlabeled training data to approximate the potential distribution of augmented classes, an unbiased risk estimator of the testing distribution can be established for the LAC problem under mild assumptions, which paves a way to develop a sound approach with theoretical guarantees. Moreover, the proposed approach can adapt to complex changing environments where augmented classes may appear and the prior of known classes may change simultaneously. Extensive experiments confirm the effectiveness of our proposed approach.

cs.LG↗

arXiv2020

Complete NLO QCD study of single- and double-quarkonium hadroproduction in the colour-evaporation model at the Tevatron and the LHC

We study the Single-Parton-Scattering (SPS) production of double quarkonia (J/psi+J/psi, J/psi+Upsilon, and Upsilon+Upsilon) in pp and pp(bar) collisions at the LHC and the Tevatron as measured by the CMS, ATLAS, LHCb, and D0 experiments in the Colour-Evaporation Model (CEM), based on the quark-hadron-duality, including Next-to-Leading Order (NLO) QCD corrections up to alpha_s^5. To do so, we also perform the first true NLO --up to alpha_s^4-- study of the p_T-differential cross section for single-quarkonium production. This allows us to fix the non-perturbative CEM parameters at NLO accuracy in the region where quarkonium-pair data are measured. Our results show that the CEM at NLO in general significantly undershoots these experimental data and, in view of the other existing SPS studies, confirm the need for Double Parton Scattering (DPS) to account for the data. Our NLO study of single-quarkonium production at mid and large p_T also confirms the difficulty of the approach to account for the measured p_T spectra; this is reminiscent of the impossibility to fit single-quarkonium data with the sole 3S18 NRQCD contribution from gluon fragmentation. We stress that the discrepancy occurs in a kinematical region where the new features of the improved CEM are not relevant.

hep-ph↗

arXiv2019

Prompt ${J/ψ}$-pair production at the LHC: impact of loop-induced contributions and of the colour-octet mechanism

Prompt double-$J/ψ$ production at high-energy hadron colliders can be considered as a golden channel to probe double parton scatterings (DPS) --in particular to study gluon-gluon correlations inside the proton-- and, at the same time, to measure the distribution of linearly-polarised gluons inside the proton. Such studies however require a good control of both single and DPS in the respective regions where they are carried out. In this context, we have critically examined two mechanisms of single parton scatterings (SPS) that may be kinematically enhanced where DPS are thought to be dominant, even though they are either at higher orders in the strong-coupling or velocity expansion. First, we have considered a gauge-invariant and infrared-safe subset of the loop-induced contribution via Colour-Singlet (CS) transitions. We have found it to become the leading CS SPS contributions at large rapidity separation, yet too small to account for the data without invoking the presence of DPS yields. Second, we have surveyed the possible Colour-Octet (CO) contributions using both old and up-to-date non-perturbative long distance matrix elements (LDMEs). We have found that the pure CO yields crucially depend on the LDMEs. Among all the LDMEs we used, only two result into a visible modification of the NRQCD (CS+CO) yield, but only in two kinematical distributions measured by ATLAS, those of the rapidity separation and of the pair invariant mass. These modifications however do not impact the control region used for their DPS study.

hep-ph↗

arXiv2019

Triple prompt $J/ψ$ hadroproduction as a hard probe of multiple-parton scatterings

We propose that the process of triple prompt $J/ψ$ hadroproduction is a very clean hard probe of multiple-parton scatterings at high-energy hadron colliders, especially the least known triple-parton scattering. A first complete study is carried out by considering single-, double-, and triple-parton scatterings coherently. Our calculation shows that it is a golden channel to probe double- and triple-parton scatterings, as the single-parton scattering is strongly suppressed. The predictions of the (differential) cross sections in proton-proton collisions at the LHC and the future higher-energy hadron colliders are given. Our study shows that its measurement is already feasible with the existing data collected during the period of the LHC run 2. A method is proposed to extract the triple-parton scattering contribution, and therefore it paves a way to study the possible triple-parton correlations in a proton.

hep-ph↗

arXiv2019

Associated Quarkonium Hadroproduction at High-Energy Colliders

Quarkonium production in proton-proton collision is interesting in profiling the partons inside the nucleon. Recently, the impact of double parton scatterings (DPSs) was suggested by experimental data of associated quarkonium production (J/psi+Z, J/psi+W, and J/psi+J/psi) at the LHC and Tevatron, in addition to single parton scatterings (SPSs). In this proceedings contribution, we review the extraction of the effective parameter of the DPS through the evaluation of the SPS contributions under quark-hadron duality.

hep-ph↗

arXiv2018

Studying parton correlations via double parton scatterings in associated quarkonium production at the LHC and the Tevatron

Quarkonium production in proton-proton (pp) collision provides interesting means to study the parton content and their correlations in the proton. Recent LHC and Tevatron data of J/psi + Z, J/psi + W and J/psi +J/psi production suggest the relevance of double parton scatterings (DPSs) as opposed to single parton scatterings (SPSs). In this proceedings contribution, we review the corresponding SPS contributions and discuss their upper limits set up by quark-hadron duality. These allow us to perform an improved extraction of the DPS yields and of their implications.

hep-ph↗

arXiv2018

Theoretical analysis of double parton scatterings in quarkonium production in proton-proton collisions at the LHC

The production process of quarkonia in proton-proton (pp) collision is a very good probe of the parton structure of the proton. Recent experimental data of the production of J/psi+vector boson or quarkonium pairs at the LHC and Tevatron suggest the relevance of double parton scatterings (DPS). We discuss here the single parton scattering (SPS) contribution to the J/psi +Z, J/psi +W, and J/psi +J/psi productions in hadron collisions. By revisiting the computations of the SPS contributions to the J/psi+Z and J/psi +W productions, we demonstrate that the ATLAS data in fact show evidence for DPS.

hep-ph↗

arXiv2016

Complete Study of Hadroproduction of a $Υ$ Meson Associated with a Prompt $J/ψ$

We present the first complete study of $Υ$ and prompt $J/ψ$ production from single-parton scattering, including the complete $\mathcal{O}(α_S^6)$ color-singlet contribution, the $\mathcal{O}(α_S^2α^2)$ electroweak contribution, the complete nonrelativistic S-wave and P-wave color-octet contribution as well as the feeddown contribution. Our study was motivated by the recent evidence reported by D0 Collaboration of prompt $J/ψ$ and $Υ$ simultaneous production at the Tevatron. With our complete evaluation, we are able to refine the determination of the double parton scattering contribution made by D0 Collaboration. We find that the effective cross section characterizing the importance of double-parton scatterings is $σ_{\rm eff}\le 8.2$ mb at $68\%$ confidence level from the D0 measurement.

hep-ph↗

arXiv2016

Study of Color Octet Matrix Elements Through $J/ψ$ Production in $e^{+}e^{-}$ Annihilation

In this paper, the color-octet long distance matrix elements are studied though the inclusive $J/ψ$ production in $e^{+}e^{-}$ annihilation within the non-relativistic QCD frame. The calculations are up-to next-to-leading order with the radiative corrections and relativistic corrections at the B-factory energy region and the near-threshold region of $4.6\sim5.6~{\rm GeV}$. A constraint of the long distance matrix elements ($\langle^1S_0^{8}\rangle$, $\langle^3P_0^{8}\rangle$) is obtained. Through our estimation, the P-wave color-octet matrix element ( $\langle0|^3P^8_0|0\rangle$ ) should be the order of $0.005m_c^2~{\rm GeV}^3$ or less. The constraint region is not compatible with the values of the long distance matrix elements fitted at hadron colliders.

hep-ph↗

arXiv2016

$B^*_{s,d} \to μ^+ μ^-$ and its impact on $B_{s,d} \to μ^+ μ^-$

The decay of $B^*_{s,d} \to μ^+ μ^-$~ and its impact on $B_{s,d} \to μ^+ μ^-$ is studied here. The $ μ^+ μ^-$ decay widths of vector mesons $B^*_{s,d}$ are about a factor of 700 larger than the corresponding scalar mesons $B_{s,d}$. The obtained ratio of the branching fractions $Br({B_{s,d}^*\to μ^+μ^-})/{Br({B_{s,d}\toμ^+μ^-})}$ is about $\frac{0.3 \times {\rm eV}}{{Γ(B^*_{s,d} \to B_{s,d} γ)}}$. At the same time, the hadronic contribution $B_{s,d} \to B^*_{s,d} γ\to μ^+ μ^-$ is estimated too. The relative increase of the amplitude of $B_{s,d}\to μ^+μ^-$ is about $(0.01\pm 0.006) \sqrt{\frac{{Γ(B^*_{s,d} \to B_{s,d} γ)}}{100~ {\rm eV}}}$. If we choose $Γ(B^*_{s,d} \to B_{s,d} γ)=2~$eV, the branching fractions of the vector mesons to lepton pair are $(6.2 \pm 0.6) \times 10^{-10}$ and $(1.7 \pm 0.2) \times 10^{-11}$ for $B^*_{s}$ and $B^*_{d}$ respectively. If we choose $Γ(B^*_{s,d} \to B_{s,d} γ)=200~$eV, the updated branching fractions of the scalar mesons to muon pair are $(3.78 \pm 0.25)\times 10^{-9}$ and $(1.09 \pm 0.09)\times 10^{-10}$ for $B_{s}$ and $B_{d}$ respectively. Further studies on $B^*_{s,d}$ are usefully here, including dielectron decay, two-body decay with $J/ψ$, and so on.

hep-ph↗