Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather independently. We observe that several methods in both representation and causal structure learning rely on the same data-generating process (DGP), namely, exchangeable but not i.i.d. (independent and identically distributed) data. We provide a unified framework, termed Identifiable Exchangeable Mechanisms (IEM), for representation and structure learning under the lens of exchangeability. IEM provides new insights that let us relax the necessary conditions for causal structure identification in exchangeable non--i.i.d. data. We also demonstrate the existence of a duality condition in identifiable representation learning, leading to new identifiability results. We hope this work will pave the way for further research in causal representation learning.
相關內容
Surface cracks in infrastructure can lead to significant deterioration and costly maintenance if not efficiently repaired. Manual repair methods are labor-intensive, time-consuming, and imprecise and thus difficult to scale to large areas. Breakthroughs in robotic perception and manipulation have advanced autonomous crack repair, but proposed methods lack end-to-end testing and adaptability to changing crack size. This paper presents an adaptive, autonomous system for surface crack detection and repair using robotics with advanced sensing technologies. The system uses an RGB-D camera for crack detection, a laser scanner for precise measurement, and an extruder and pump for material deposition. A novel validation procedure with 3D-printed crack specimens simulates real-world cracks and ensures testing repeatability. Our study shows that an adaptive system for crack filling is more efficient and effective than a fixed-speed approach, with experimental results confirming precision and consistency. This research paves the way for versatile, reliable robotic infrastructure maintenance.
Applications from manipulation to autonomous vehicles rely on robust and general object tracking to safely perform tasks in dynamic environments. We propose the first certifiably optimal category-level approach for simultaneous shape estimation and pose tracking of an object of known category (e.g. a car). Our approach uses 3D semantic keypoint measurements extracted from an RGB-D image sequence, and phrases the estimation as a fixed-lag smoothing problem. Temporal constraints enforce the object's rigidity (fixed shape) and smooth motion according to a constant-twist motion model. The solutions to this problem are the estimates of the object's state (poses, velocities) and shape (paramaterized according to the active shape model) over the smoothing horizon. Our key contribution is to show that despite the non-convexity of the fixed-lag smoothing problem, we can solve it to certifiable optimality using a small-size semidefinite relaxation. We also present a fast outlier rejection scheme that filters out incorrect keypoint detections with shape and time compatibility tests, and wrap our certifiable solver in a graduated non-convexity scheme. We evaluate the proposed approach on synthetic and real data, showcasing its performance in a table-top manipulation scenario and a drone-based vehicle tracking application.
As Diffusion Models have shown promising performance, a lot of efforts have been made to improve the controllability of Diffusion Models. However, how to train Diffusion Models to have the disentangled latent spaces and how to naturally incorporate the disentangled conditions during the sampling process have been underexplored. In this paper, we present a training framework for feature disentanglement of Diffusion Models (FDiff). We further propose two sampling methods that can boost the realism of our Diffusion Models and also enhance the controllability. Concisely, we train Diffusion Models conditioned on two latent features, a spatial content mask, and a flattened style embedding. We rely on the inductive bias of the denoising process of Diffusion Models to encode pose/layout information in the content feature and semantic/style information in the style feature. Regarding the sampling methods, we first generalize Composable Diffusion Models (GCDM) by breaking the conditional independence assumption to allow for some dependence between conditional inputs, which is shown to be effective in realistic generation in our experiments. Second, we propose timestep-dependent weight scheduling for content and style features to further improve the performance. We also observe better controllability of our proposed methods compared to existing methods in image manipulation and image translation.
Diffusion models have shown strong competitiveness in offline reinforcement learning tasks by formulating decision-making as sequential generation. However, the practicality of these methods is limited due to the lengthy inference processes they require. In this paper, we address this problem by decomposing the sampling process of diffusion models into two decoupled subprocesses: 1) generating a feasible trajectory, which is a time-consuming process, and 2) optimizing the trajectory. With this decomposition approach, we are able to partially separate efficiency and quality factors, enabling us to simultaneously gain efficiency advantages and ensure quality assurance. We propose the Trajectory Diffuser, which utilizes a faster autoregressive model to handle the generation of feasible trajectories while retaining the trajectory optimization process of diffusion models. This allows us to achieve more efficient planning without sacrificing capability. To evaluate the effectiveness and efficiency of the Trajectory Diffuser, we conduct experiments on the D4RL benchmarks. The results demonstrate that our method achieves $\it 3$-$\it 10 \times$ faster inference speed compared to previous sequence modeling methods, while also outperforming them in terms of overall performance. //github.com/RenMing-Huang/TrajectoryDiffuser Keywords: Reinforcement Learning and Efficient Planning and Diffusion Model
Quantum computers are gaining importance in various applications like quantum machine learning and quantum signal processing. These applications face significant challenges in loading classical datasets into quantum memory. With numerous algorithms available and multiple quality attributes to consider, comparing data loading methods is complex. Our objective is to compare (in a structured manner) various algorithms for loading classical datasets into quantum memory (by converting statevectors to circuits). We evaluate state preparation algorithms based on five key attributes: circuit depth, qubit count, classical runtime, statevector representation (dense or sparse), and circuit alterability. We use the Pareto set as a multi-objective optimization tool to identify algorithms with the best combination of properties. To improve comprehension and speed up comparisons, we also visually compare three metrics (namely, circuit depth, qubit count, and classical runtime). We compare seven algorithms for dense statevector conversion and six for sparse statevector conversion. Our analysis reduces the initial set of algorithms to two dense and two sparse groups, highlighting inherent trade-offs. This comparison methodology offers a structured approach for selecting algorithms based on specific needs. Researchers and practitioners can use it to help select data-loading algorithms for various quantum computing tasks.
Modelling and characterizing emergent behaviour within a swarm can pose significant challenges in terms of 'assurance'. Assurance tasks encompass adherence to standards, certification processes, and the execution of verification and validation (V&V) methods, such as model checking. In this study, we propose a holistic, multi-level modelling approach for formally verifying and validating autonomous robotic swarms, which are defined at the macroscopic formal modelling, low-fidelity simulation, high-fidelity simulation, and real-robot levels. Our formal macroscopic models, used for verification, are characterized by data derived from actual simulations, ensuring both accuracy and traceability across different system models. Furthermore, our work combines formal verification with experimental validation involving real robots. In this way, our corroborative approach for V&V seeks to enhance confidence in the evidence, in contrast to employing these methods separately. We explore our approach through a case study focused on a swarm of robots operating within a public cloakroom.
Score-based generative models have emerged as a powerful approach for sampling high-dimensional probability distributions. Despite their effectiveness, their theoretical underpinnings remain relatively underdeveloped. In this work, we study the convergence properties of deterministic samplers based on probability flow ODEs from both theoretical and numerical perspectives. Assuming access to $L^2$-accurate estimates of the score function, we prove the total variation between the target and the generated data distributions can be bounded above by $\mathcal{O}(d^{3/4}\delta^{1/2})$ in the continuous time level, where $d$ denotes the data dimension and $\delta$ represents the $L^2$-score matching error. For practical implementations using a $p$-th order Runge-Kutta integrator with step size $h$, we establish error bounds of $\mathcal{O}(d^{3/4}\delta^{1/2} + d\cdot(dh)^p)$ at the discrete level. Finally, we present numerical studies on problems up to 128 dimensions to verify our theory.
To fill the gap of traditional GS compression method, in this paper, we first propose a simple and effective GS data compression anchor called Graph-based GS Compression (GGSC). GGSC is inspired by graph signal processing theory and uses two branches to compress the primitive center and attributes. We split the whole GS sample via KDTree and clip the high-frequency components after the graph Fourier transform. Followed by quantization, G-PCC and adaptive arithmetic coding are used to compress the primitive center and attribute residual matrix to generate the bitrate file. GGSS is the first work to explore traditional GS compression, with advantages that can reveal the GS distortion characteristics corresponding to typical compression operation, such as high-frequency clipping and quantization. Second, based on GGSC, we create a GS Quality Assessment dataset (GSQA) with 120 samples. A subjective experiment is conducted in a laboratory environment to collect subjective scores after rendering GS into Processed Video Sequences (PVS). We analyze the characteristics of different GS distortions based on Mean Opinion Scores (MOS), demonstrating the sensitivity of different attributes distortion to visual quality. The GGSC code and the dataset, including GS samples, MOS, and PVS, are made publicly available at //github.com/Qi-Yangsjtu/GGSC.
In nonparameteric Bayesian approaches, Gaussian stochastic processes can serve as priors on real-valued function spaces. Existing literature on the posterior convergence rates under Gaussian process priors shows that it is possible to achieve optimal or near-optimal posterior contraction rates if the smoothness of the Gaussian process matches that of the target function. Among those priors, Gaussian processes with a parametric Mat\'ern covariance function is particularly notable in that its degree of smoothness can be determined by a dedicated smoothness parameter. \citet{ma2022beyond} recently introduced a new family of covariance functions called the Confluent Hypergeometric (CH) class that simultaneously possess two parameters: one controls the tail index of the polynomially decaying covariance function, and the other parameter controls the degree of mean-squared smoothness analogous to the Mat\'ern class. In this paper, we show that with proper choice of rescaling parameters in the Mat\'ern and CH covariance functions, it is possible to obtain the minimax optimal posterior contraction rate for $\eta$-regular functions for nonparametric regression model with fixed design. Unlike the previous results for unrescaled cases, the smoothness parameter of the covariance function need not equal $\eta$ for achieving the optimal minimax rate, for either rescaled Mat\'ern or rescaled CH covariances, illustrating a key benefit for rescaling. We also consider a fully Bayesian treatment of the rescaling parameters and show the resulting posterior distributions still contract at the minimax-optimal rate. The resultant hierarchical Bayesian procedure is fully adaptive to the unknown true smoothness.
The success of AI models relies on the availability of large, diverse, and high-quality datasets, which can be challenging to obtain due to data scarcity, privacy concerns, and high costs. Synthetic data has emerged as a promising solution by generating artificial data that mimics real-world patterns. This paper provides an overview of synthetic data research, discussing its applications, challenges, and future directions. We present empirical evidence from prior art to demonstrate its effectiveness and highlight the importance of ensuring its factuality, fidelity, and unbiasedness. We emphasize the need for responsible use of synthetic data to build more powerful, inclusive, and trustworthy language models.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191