Low-Rank Approximation of Structural Redundancy for Self-Supervised Learning

We study the data-generating mechanism for reconstructive SSL to shed light on its effectiveness. With an infinite amount of labeled samples, we provide a sufficient and necessary condition for perfect linear approximation. The condition reveals a full-rank component that preserves the label classes of Y, along with a redundant component. Motivated by the condition, we propose to approximate the redundant component by a low-rank factorization and measure the approximation quality by introducing a new quantity $\epsilon_s$, parameterized by the rank of factorization s. We incorporate $\epsilon_s$ into the excess risk analysis under both linear regression and ridge regression settings, where the latter regularization approach is to handle scenarios when the dimension of the learned features is much larger than the number of labeled samples n for downstream tasks. We design three stylized experiments to compare SSL with supervised learning under different settings to support our theoretical findings.

PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models

Personalized text-to-image generation has emerged as a powerful and sought-after tool, empowering users to create customized images based on their specific concepts and prompts. However, existing approaches to personalization encounter multiple challenges, including long tuning times, large storage requirements, the necessity for multiple input images per identity, and limitations in preserving identity and editability. To address these obstacles, we present PhotoVerse, an innovative methodology that incorporates a dual-branch conditioning mechanism in both text and image domains, providing effective control over the image generation process. Furthermore, we introduce facial identity loss as a novel component to enhance the preservation of identity during training. Remarkably, our proposed PhotoVerse eliminates the need for test time tuning and relies solely on a single facial photo of the target identity, significantly reducing the resource cost associated with image generation. After a single training phase, our approach enables generating high-quality images within only a few seconds. Moreover, our method can produce diverse images that encompass various scenes and styles. The extensive evaluation demonstrates the superior performance of our approach, which achieves the dual objectives of preserving identity and facilitating editability. Project page: https://photoverse2d.github.io/

AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose

Creating expressive, diverse and high-quality 3D avatars from highly customized text descriptions and pose guidance is a challenging task, due to the intricacy of modeling and texturing in 3D that ensure details and various styles (realistic, fictional, etc). We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance. In specific, we introduce a 2D diffusion model conditioned on DensePose signal to establish 3D pose control of avatars through 2D images, which enhances view consistency from partially observed scenarios. It addresses the infamous Janus Problem and significantly stablizes the generation process. Moreover, we propose a progressive high-resolution 3D synthesis strategy, which obtains substantial improvement over the quality of the created 3D avatars. To this end, the proposed AvatarVerse pipeline achieves zero-shot 3D modeling of 3D avatars that are not only more expressive, but also in higher quality and fidelity than previous works. Rigorous qualitative evaluations and user studies showcase AvatarVerse's superiority in synthesizing high-fidelity 3D avatars, leading to a new standard in high-quality and stable 3D avatar creation. Our project page is: https://avatarverse3d.github.io

Generalized Invariant Matching Property via LASSO

Learning under distribution shifts is a challenging task. One principled approach is to exploit the invariance principle via the structural causal models. However, the invariance principle is violated when the response is intervened, making it a difficult setting. In a recent work, the invariant matching property has been developed to shed light on this scenario and shows promising performance. In this work, we generalize the invariant matching property by formulating a high-dimensional problem with intrinsic sparsity. We propose a more robust and computation-efficient algorithm by leveraging a variant of Lasso, improving upon the existing algorithms.

Learning Invariant Representations under General Interventions on the Response

It has become increasingly common nowadays to collect observations of feature and response pairs from different environments. As a consequence, one has to apply learned predictors to data with a different distribution due to distribution shifts. One principled approach is to adopt the structural causal models to describe training and test models, following the invariance principle which says that the conditional distribution of the response given its predictors remains the same across environments. However, this principle might be violated in practical settings when the response is intervened. A natural question is whether it is still possible to identify other forms of invariance to facilitate prediction in unseen environments. To shed light on this challenging scenario, we introduce invariant matching property (IMP) which is an explicit relation to capture interventions through an additional feature. This leads to an alternative form of invariance that enables a unified treatment of general interventions on the response. We analyze the asymptotic generalization errors of our method under both the discrete and continuous environment settings, where the continuous case is handled by relating it to the semiparametric varying coefficient models. We present algorithms that show competitive performance compared to existing methods over various experimental settings.

An Invariant Matching Property for Distribution Generalization under Intervened Response

The task of distribution generalization concerns making reliable prediction of a response in unseen environments. The structural causal models are shown to be useful to model distribution changes through intervention. Motivated by the fundamental invariance principle, it is often assumed that the conditional distribution of the response given its predictors remains the same across environments. However, this assumption might be violated in practical settings when the response is intervened. In this work, we investigate a class of model with an intervened response. We identify a novel form of invariance by incorporating the estimates of certain features as additional predictors. Effectively, we show this invariance is equivalent to having a deterministic linear matching that makes the generalization possible. We provide an explicit characterization of the linear matching and present our simulation results under various intervention settings.

Causal Inference Using Linear Time-Varying Filters with Additive Noise

Causal inference using the restricted structural causal model framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms. For linear models and additive noise models, the asymmetry arises from non-Gaussianity or non-linearity, respectively. This methodology can be adapted to stationary time series, however, inferring causal relationships from non-stationary time series remains a challenging task. In the work, we focus on slowly-varying nonstationary processes and propose to break the symmetry by exploiting the nonstationarity of the data. Our main theoretical result shows that causal direction is identifiable in generic cases when cause and effect are connected via a time-varying filter. We propose a causal discovery procedure by leveraging powerful estimates of the bivariate evolutionary spectra. Both synthetic and real-world data simulations that involve high-order and nonsmooth filters are provided to demonstrate the effectiveness of our proposed methodology.