arXiv subjects
Publications and source records attributed to Lijun Chen.
We provide an expository introduction on the importance of higher-arity tensor operations to deep learning. Then, we conduct a novel empirical investigation of higher-arity phenomenon in trained neural networks, introduce a hypergraphical generalization of the multilayer perceptron, and explore connections to evolutionary algorithms. We conclude with a discussion of promising directions for future research.
3D Gaussian Splatting (3DGS) delivers real-time and high-fidelity rendering but remains challenged by unconstrained in-the-wild scenes, where drastic appearance variations and transient objects violate multi-view consistency. Existing methods are fundamentally limited by independent and discrete embeddings that struggle to capture continuous environmental changes or model spatially-varying local illumination. To address these limitations, we propose \textbf{WilLaGS}, a unified framework for robust 3D scene reconstruction and generative appearance synthesis under unconstrained settings. Specifically, we introduce a generative appearance model where a $\beta$-VAE learns a structured and continuous manifold of global appearance. Conditioned on the latent code, we construct a 3D neural appearance field that generates dynamic Tri-Plane features to encode spatially-varying local illumination effects. Furthermore, to suppress transient artifacts, we present a self-supervised perceptual masking mechanism that leverages a Teacher-Student (EMA) architecture to derive a stable scene consensus, robustly identifying inconsistent regions via perceptual discrepancies. Extensive experiments on multiple datasets demonstrate that \textbf{WilLaGS} achieves state-of-the-art performance in reconstruction quality and novel view appearance synthesis, while maintaining real-time rendering efficiency.
We study stochastic multi-armed bandits on dynamic graphs, where arms correspond to the vertices of a network with time-varying edges. In this setting, the learner is restricted to local movement, selecting only its current node or an immediate neighbor at each round. This constraint decouples best-arm identification from exploitation: even after the optimal arm is identified, the learner may remain unable to reach it through the evolving topology. We identify a process-agnostic structural condition, based on sliding-window mixing, that ensures the graph's intrinsic walk remains stable for both exploration and navigation. Under this regime, we analyze a family of local explore-then-commit algorithms and establish sublinear expected regret. Our framework includes a reward-aware strategy, for which we prove a worst-case safety theorem and a separate performance gain theorem.
We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations -- lower level information that is often abstracted. Our framework enables two novel objectives: (1) analysis of the evolution of architectural complexity over deep learning history, and (2) automatic construction of novel architectures based on new types of tensor operations. Our study of DNNs introduced over the past 40 years reveals a connection between groundbreaking architectures and increases in different types of architectural complexity. Moreover, we identify several large classes of higher complexity architectures that have not yet been explored. We then collect a dataset of 3,000+ higher complexity architectures, which we publicly release at: https://github.com/combinatoriallabs/ArchitecturalComplexity.
On the periphery of galaxy clusters, moderately high galaxy densities and velocity dispersions favour interactions and mergers that influence galaxy evolution prior to cluster infall. Observational studies of this phase in dwarfs remain rare. We present a high-resolution study of the merger remnant VCC 693 in the outskirts of Virgo cluster, using observations from the Atomic gas in Virgo Interacting Dwarf galaxies (AVID) project. We explore the origin of VCC 693 and the consequences of the merger on its star formation and structure through a joint analysis of VLA and FAST HI emission line observations, together with complementary optical imaging and spectroscopy. We employ hydrodynamical simulations to help interpret the observations. Our analysis favours a near-major merger between two dwarfs with a stellar mass ratio of 3:1-4:1, with one likely gas-poor progenitor (i.e., a damp merger). The optical appearance of VCC 693 is dominated by complex tidal structures throughout the system, whereas the HI gas has settled to a regular rotating disk. Compared with similar-mass dwarfs, the central star formation and gas-phase metallicity are moderately enhanced. The global star formation rate, HI gas content, and HI-to-optical size ratio of VCC 693 are broadly consistent with those of typical dwarfs of similar mass, albeit somewhat lower. Decomposition of the HI rotation curve into baryonic and dark matter indicates a high halo concentration, suggesting post-merger relaxation into a more centrally peaked configuration. Together with two recent studies of AVID post-merger systems, these results support the view that even major dwarf mergers can produce remnants with overall stellar structures indistinguishable from ordinary dwarfs, and that the environmental effects in cluster outskirts can promote damp or mixed mergers, constituting an integral part of galactic pre-processing.
Stellar halos are the only major stellar component of disk galaxies that lack systematic observational characterization, yet they encode critical information about galaxy merger histories. We present the first systematic census of stellar halos in a large, flux-limited sample of 169 high-inclination central galaxies with stellar masses 7.3 <= log Mstar/Msun <= 11.0 and redshift z < 0.1, using HSC-SSP Deep optical images. Stellar halos are detected in 93 galaxies, primarily through their low isophotal ellipticities in the outskirts, improving upon conventional methods of stellar halo identification. The halo detection rate reaches ~ 50% at log Mstar/Msun > 9.9 and >= 70% for Milky Way (MW)-mass galaxies. We derive halo surface brightness profiles, colors, and masses, finding that stellar halos generally follow power-law radial profiles. Higher-mass galaxies, on average, exhibit smaller power-law indices and larger halo mass fractions, indicating more extended halos and more active merger histories. A significant stellar halo color-mass correlation, driven mainly by the mass-metallicity relation, suggests dominance by a few massive accretion events. MW-mass galaxies have a median stellar halo fraction of 10% +/- 5%. Among nearby galaxies with halo measurements within 25 Mpc, two thirds (including the MW) lie below the mean stellar halo fraction-galaxy mass relation. Overall, the nearby galaxies show a median halo deficit of ~ 0.3 dex, implying unusually quiescent merger histories. We show that this deficit follows a broader trend in which typical halo fractions increase with heliocentric distance, tracking the gradual rise in matter density toward the cosmic average by z <= 0.07.
Scalable methods for networked multi-agent reinforcement learning let each agent plan using only a small neighborhood of the agent graph. This works only when the system is value-local, meaning a perturbation at one agent affects the long-run value at another agent weakly when the two are far apart. In the average-reward setting, the standard way to certify locality is the Dobrushin row-sum bound on a single matrix $C^\pi$ that captures how each agent's next state depends on each other agent's current state. To make this matrix easy to work with, prior work bounds it by a supremum over joint actions. The resulting bound is independent of the policy, but it is loose whenever the policy never picks the worst-case action. We split $C^\pi$ into pieces that separately track environment sensitivity and policy sensitivity, $C^\pi \preceq E^{\mathrm s}+E^{\mathrm a}\Pi(\pi)$, where $E^{\mathrm s}$ measures how the next state moves with the current state, $E^{\mathrm a}$ measures how it moves with the current action, and $\Pi(\pi)$ measures how reactive the policy is to changes in state. The spectral radius of $H^\pi := E^{\mathrm s}+E^{\mathrm a}\Pi(\pi)$ then controls the decay of the average-reward Poisson solution, and the spectral certificate $\rho(H^\pi)<1$ is strictly weaker than the row-sum condition $\|H^\pi\|_\infty<1$ on the same matrix and applies in regimes where policy-independent action-supremum bounds used in prior Dobrushin-style work cannot. For temperature-$\tau$ softmax policies we get $\Pi(\pi)\le L/(2\tau)$, so the softmax temperature directly controls locality. We use this decay result to give a deterministic oracle guarantee for a block-coordinate KL-proximal policy-improvement template whose truncation bias decays exponentially in the message-passing radius $\kappa$.
We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, where accessibility of the next action is restricted to a subset dependent on the agent's current choice. We formalize these constraints through stochastically evolving graphs where actions are limited to local neighborhoods. This mobility-constrained structure imposes a dual challenge: the statistical requirement of information acquisition and the physical overhead of navigation. We analyze FMAB under i.i.d. Erd\H{o}s--R'enyi and Edge-Markovian process, proposing a two-phase lazy random walk algorithm for robust exploration. We establish high-probability sublinear regret bounds and prove near-optimality via a matching information-theoretic lower bound. Our results characterize the intrinsic cost of learning under local-move constraints, complemented by a robotic disaster-response simulation.
We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward. Our objective is to design a communication-free policy that maximizes collective reward, while separating coordination costs from learning costs. We propose a modular protocol that first solves the multi-agent coordination problem by identifying and seating players on distinct, high-value regions via a novel maxima-directed search and then decouples the problem into $N$ independent single-player Lipschitz bandits. In the consensus regime, we obtain an end-to-end regret bound whose dominant learning term is \(\tilde{O}(T^{(d+1)/(d+2)})\), matching the single-player Lipschitz rate; the upfront coordination cost is horizon-independent at fixed confidence and only polylogarithmic in \(T\) in the expected-regret form. Under an additional public coverage/scheduling assumption for the epochic extension, we also obtain a gap-free \(\tilde{O}(T^{(d+1)/(d+2)})\) guarantee. We further derive a matching lower bound for the dominant learning term and extend the framework to general distance-threshold collision models.
Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class scores) and intermediate layer features (i.e., latent representations). Unlike previous approaches, we propose a feature KD framework for training the student's backbone using feature-based losses exclusively (i.e., without logit-based losses such as cross entropy). Leveraging recent discoveries about the geometry of latent representations, we introduce a knowledge quality metric for identifying which teacher layers provide the most effective knowledge for distillation. Experiments on three image classification datasets with four diverse student-teacher pairs, spanning convolutional neural networks and vision transformers, demonstrate our KD method achieves state-of-the-art performance, delivering top-1 accuracy boosts of up to 15% over standard approaches. We publically share our code to facilitate future work at https://github.com/Thegolfingocto/KD_wo_CE.
We study incentivized exploration in multi-armed bandit (MAB) settings with infinitely many arms modeled as elements in continuous metric spaces. Unlike classical bandit models, we consider scenarios where the decision-maker (principal) incentivizes myopic agents to explore beyond their greedy choices through compensation, but with the complication of reward drift--biased feedback arising due to the incentives. We propose novel incentivized exploration algorithms that discretize the infinite arm space uniformly and demonstrate that these algorithms simultaneously achieve sublinear cumulative regret and sublinear total compensation. Specifically, we derive regret and compensation bounds of $\Tilde{O}(T^{d+1/d+2})$, with $d$ representing the covering dimension of the metric space. Furthermore, we generalize our results to contextual bandits, achieving comparable performance guarantees. We validate our theoretical findings through numerical simulations.
The origin of extragalactic, almost dark HI clouds with extreme gas-to-stellar mass ratios remains poorly understood. We investigate the nature and fate of the "almost dark" cloud AGC 226178, projected within the Virgo cluster, with an HI-to-stellar mass ratio of ~1000. We present deep single-dish HI mapping from the Five-hundred-meter Aperture Spherical Telescope (FAST), complemented by high-resolution interferometric data from the Very Large Array (VLA), as part of the Atomic gas in Virgo Interacting Dwarf galaxies (AVID) project. These observations provide the highest-quality HI analysis to date of such a cloud, combining resolution and sensitivity. FAST data reveal a short, low-velocity tail toward the dwarf galaxy VCC 2034, previously proposed as a possible origin for AGC 226178. However, VCC 2034 shows a line-of-sight asymmetric HI feature and cometary morphology indicating a stripping event unrelated to AGC 226178. VLA data reveal a velocity gradient across AGC 226178 and a clumpy internal structure. The velocity dispersion exceeds the thermal linewidth, implying turbulence or unresolved motions. The cloud cannot be gravitationally bound by atomic gas alone. The resolved HI clumps follow standard HI mass-star formation rate and mass-size relations, with those forming stars reaching surface densities above the threshold for self-shielding. We conclude that AGC 226178 is a free-floating HI cloud of unknown origin. The system appears to be in the process of disintegration. It is likely located well outside the Virgo cluster, as the preservation of its extended HI morphology within the cluster environment would otherwise require a substantial reservoir of unseen molecular gas with a mass exceeding that of the observed HI content. While confinement pressure from the hot intracluster medium may aid its stability, it is unlikely to be the dominant factor preventing its disruption.
We propose a 3D Gaussian splatting-based framework for outdoor relighting that leverages intrinsic image decomposition to precisely integrate sunlight, sky radiance, and indirect lighting from unconstrained photo collections. Unlike prior methods that compress the per-image global illumination into a single latent vector, our approach enables simultaneously diverse shading manipulation and the generation of dynamic shadow effects. This is achieved through three key innovations: (1) a residual-based sun visibility extraction method to accurately separate direct sunlight effects, (2) a region-based supervision framework with a structural consistency loss for physically interpretable and coherent illumination decomposition, and (3) a ray-tracing-based technique for realistic shadow simulation. Extensive experiments demonstrate that our framework synthesizes novel views with competitive fidelity against state-of-the-art relighting solutions and produces more natural and multifaceted illumination and shadow effects.
In recent years, with the rapid development of science and technology, heterogeneous treatment effects have emerged as a focal research topic in statistics, econometrics, and sociology. This paper investigates HTE through semiparametric single-index models based on doubly robust estimation. Departing from conventional approaches, we neither impose boundedness constraints on the link function in single-index models nor restrict its support range. By employing the sieve method to approximate the link function, we achieve simultaneous estimation of both the link function and index parameters. Our study not only establishes the asymptotic properties of the proposed estimator but also systematically evaluates its finite-sample performance through comprehensive simulation studies. Numerical results demonstrate that our method significantly outperforms other commonly used competing estimators. Furthermore, we apply the proposed approach to the National Health and Nutrition Examination Survey dataset to assess the impact of participation in school lunch programs on body mass index.
Dwarf-dwarf galaxy mergers are among the least explored aspects of dwarf galaxy pre-processing as they fall into clusters. We present the first case study of a coalesced late-type dwarf major merger (VCC 479; stellar mass $\sim\,8\,\times\,10^7\,\rm M_\odot$) that has undergone significant environmental influence, with the aim of exploring dwarf galaxy evolution under the combined effects of galaxy interactions and environmental processes, and understanding its relevance to the diversity of dwarf galaxies in cluster environments. Our analysis is based on VLA and FAST HI emission line mapping from the Atomic gas in Virgo Interacting Dwarf galaxies (AVID) survey. We also perform idealized hydrodynamical simulations of dwarf-dwarf mergers to help interpret the observations. We identify symmetric stellar shell structures in VCC 479, indicative of a coalesced major merger of dwarf galaxies. The galaxy features a central starburst, initiated $\sim$600 Myr ago, embedded within an exponential disk quenched $\sim$1 Gyr ago. The starburst contributes only 2.9$\pm$0.5\% of the total stellar mass, and VCC 479's global star formation rate is 0.3 dex lower than typical dwarfs of similar mass. The galaxy is highly HI deficient, with most HI gas concentrated within the central 1 kpc and little extended HI envelope. The misalignment of the HI velocity field with the stellar body is best explained by merger-triggered gas inflow, as seen in our simulations. Our analysis is consistent with a scenario that the majority of HI gas of the progenitor galaxies was removed by the cluster environment prior to the final coalescence. The merger concentrates the remaining gas toward the galaxy center, triggering a central starburst. The combined effect of environment stripping and galaxy merger has transformed VCC 479 into a blue-core dwarf undergoing morphological transition from a late-type to an early-type galaxy.
According to the standard inside-out galaxy formation scenario, galaxies first form a dense core and then gradually assemble their outskirts. This implies that galaxies with similar central stellar mass densities might have evolutionary links. We use the UVJ color-color diagram to select quiescent galaxies in the redshift interval from 0.5 to 2.5 and classify them into different subsamples based on their central stellar mass densities, stellar mass, morphological type and redshift. We then infer the intrinsic axis ratios $μ_{B/A}$ and $μ_{C/A}$ of different subsamples based on the apparent axis ratio $q$ distributions, where A, B, and C refers to, respectively, the major, intermediate and minor axis of a triaxial ellipsoidal model. We find that 1) massive quiescent galaxies have typical intrinsic shapes similarly close to thick oblate structures, with $μ_{B/A} \gtrsim 0.9$, regardless of stellar mass, redshift, or central stellar mass densities, and 2) galaxies at higher redshift are systematically thinner than their lower-redshift counterparts, and 3) when splitting the sample into early type and late type with Sersic indices, ETGs at higher redshift are slightly more prolate (smaller average $μ_{B/A}$) than those at lower redshift. Minor mergers of galaxies may have played important roles in the structural evolution of quiescent galaxies found in this work.
Effective multi-agent collaboration is imperative for solving complex, distributed problems. In this context, two key challenges must be addressed: first, autonomously identifying optimal objectives for collective outcomes; second, aligning these objectives among agents. Traditional frameworks, often reliant on centralized learning, struggle with scalability and efficiency in large multi-agent systems. To overcome these issues, we introduce a decentralized state-based value learning algorithm that enables agents to independently discover optimal states. Furthermore, we introduce a novel mechanism for multi-agent interaction, wherein less proficient agents follow and adopt policies from more experienced ones, thereby indirectly guiding their learning process. Our theoretical analysis shows that our approach leads decentralized agents to an optimal collective policy. Empirical experiments further demonstrate that our method outperforms existing decentralized state-based and action-based value learning strategies by effectively identifying and aligning optimal objectives.
We study incentivized exploration for the multi-armed bandit (MAB) problem with non-stationary reward distributions, where players receive compensation for exploring arms other than the greedy choice and may provide biased feedback on the reward. We consider two different non-stationary environments: abruptly-changing and continuously-changing, and propose respective incentivized exploration algorithms. We show that the proposed algorithms achieve sublinear regret and compensation over time, thus effectively incentivizing exploration despite the nonstationarity and the biased or drifted feedback.