Label Distribution Learning (LDL) is a novel machine learning paradigm that addresses the problem of label ambiguity and has found widespread applications. Obtaining complete label distributions in real-world scenarios is challenging, which has led to the emergence of Incomplete Label Distribution Learning (InLDL). However, the existing InLDL methods overlook a crucial aspect of LDL data: the inherent imbalance in label distributions. To address this limitation, we propose \textbf{Incomplete and Imbalance Label Distribution Learning (I\(^2\)LDL)}, a framework that simultaneously handles incomplete labels and imbalanced label distributions. Our method decomposes the label distribution matrix into a low-rank component for frequent labels and a sparse component for rare labels, effectively capturing the structure of both head and tail labels. We optimize the model using the Alternating Direction Method of Multipliers (ADMM) and derive generalization error bounds via Rademacher complexity, providing strong theoretical guarantees. Extensive experiments on 15 real-world datasets demonstrate the effectiveness and robustness of our proposed framework compared to existing InLDL methods.

Recommenders take place on a wide scale of e-commerce systems, reducing the problem of information overload. The most common approach is to choose a recommender used by the system to make predictions. However, users vary from each other; thus, a one-fits-all approach seems to be sub-optimal. In this paper, we propose a meta-hybrid recommender that uses machine learning to predict an optimal algorithm. In this way, the best-performing recommender is used for each specific session and user. This selection depends on contextual and preferential information collected about the user. We use standard MovieLens and The Movie DB datasets for offline evaluation. We show that based on the proposed model, it is possible to predict which recommender will provide the most precise recommendations to a user. The theoretical performance of our meta-hybrid outperforms separate approaches by 20-50% in normalized Discounted Gain and Root Mean Square Error metrics. However, it is hard to obtain the optimal performance based on widely-used standard information stored about users.

Recent studies have shown that many nonconvex machine learning problems meet a so-called generalized-smooth condition that extends beyond traditional smooth nonconvex optimization. However, the existing algorithms designed for generalized-smooth nonconvex optimization encounter significant limitations in both their design and convergence analysis. In this work, we first study deterministic generalized-smooth nonconvex optimization and analyze the convergence of normalized gradient descent under the generalized Polyak-Lojasiewicz condition. Our results provide a comprehensive understanding of the interplay between gradient normalization and function geometry. Then, for stochastic generalized-smooth nonconvex optimization, we propose an independently-normalized stochastic gradient descent algorithm, which leverages independent sampling, gradient normalization and clipping to achieve an $\mathcal{O}(\epsilon^{-4})$ sample complexity under relaxed assumptions. Experiments demonstrate the fast convergence of our algorithm.

Adversarial Imitation Learning is traditionally framed as a two-player zero-sum game between a learner and an adversarially chosen cost function, and can therefore be thought of as the sequential generalization of a Generative Adversarial Network (GAN). However, in recent years, diffusion models have emerged as a non-adversarial alternative to GANs that merely require training a score function via regression, yet produce generations of a higher quality. In response, we investigate how to lift insights from diffusion modeling to the sequential setting. We propose diffusing states and performing score-matching along diffused states to measure the discrepancy between the expert's and learner's states. Thus, our approach only requires training score functions to predict noises via standard regression, making it significantly easier and more stable to train than adversarial methods. Theoretically, we prove first-and second-order instance-dependent bounds with linear scaling in the horizon, proving that our approach avoids the compounding errors that stymie offline approaches to imitation learning. Empirically, we show our approach outperforms both GAN-style imitation learning baselines and discriminator-free imitation learning baselines across various continuous control problems, including complex tasks like controlling humanoids to walk, sit, crawl, and navigate through obstacles. Fundamentally, in imitation learning (IL, Osa et al. (2018)), we want to match the sequential behavior of an expert demonstrator. Different notions of what matching should mean for IL have been proposed in the literature, from f-divergences (Ho & Ermon, 2016; Ke et al., 2021) to Integral Probability Metrics (IPMs, Müller (1997); Sun et al. (2019); Kidambi et al. (2021); Swamy et al. (2021); Chang et al. (2021); Song et al. (2024)). To compute the chosen notion of divergence from the expert demonstrations so that the learner can then optimize it, it is common to train a discriminator (i.e. a classifier) between expert and learner data. This discriminator is then used as a reward function for a policy update, an approach known as inverse reinforcement learning (IRL, Abbeel & Ng (2004); Ziebart et al. (2008)).

This paper reports on a novel method for LiDAR odometry estimation, which completely parameterizes the system with dual quaternions. To accomplish this, the features derived from the point cloud, including edges, surfaces, and Stable Triangle Descriptor (STD), along with the optimization problem, are expressed in the dual quaternion set. This approach enables the direct combination of translation and orientation errors via dual quaternion operations, greatly enhancing pose estimation, as demonstrated in comparative experiments against other state-of-the-art methods. Our approach reduced drift error compared to other LiDAR-only-odometry methods, especially in scenarios with sharp curves and aggressive movements with large angular displacement. DualQuat-LOAM is benchmarked against several public datasets. In the KITTI dataset it has a translation and rotation error of 0.79% and 0.0039{\deg}/m, with an average run time of 53 ms.

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos.

Sparse Principal Component Analysis (Sparse PCA) is a pivotal tool in data analysis and dimensionality reduction. However, Sparse PCA is a challenging problem in both theory and practice: it is known to be NP-hard and current exact methods generally require exponential runtime. In this paper, we propose a novel framework to efficiently approximate Sparse PCA by (i) approximating the general input covariance matrix with a re-sorted block-diagonal matrix, (ii) solving the Sparse PCA sub-problem in each block, and (iii) reconstructing the solution to the original problem. Our framework is simple and powerful: it can leverage any off-the-shelf Sparse PCA algorithm and achieve significant computational speedups, with a minor additive error that is linear in the approximation error of the block-diagonal matrix. Suppose $g(k, d)$ is the runtime of an algorithm (approximately) solving Sparse PCA in dimension $d$ and with sparsity value $k$. Our framework, when integrated with this algorithm, reduces the runtime to $\mathcal{O}\left(\frac{d}{d^\star} \cdot g(k, d^\star) + d^2\right)$, where $d^\star \leq d$ is the largest block size of the block-diagonal matrix. For instance, integrating our framework with the Branch-and-Bound algorithm reduces the complexity from $g(k, d) = \mathcal{O}(k^3\cdot d^k)$ to $\mathcal{O}(k^3\cdot d \cdot (d^\star)^{k-1})$, demonstrating exponential speedups if $d^\star$ is small. We perform large-scale evaluations on many real-world datasets: for exact Sparse PCA algorithm, our method achieves an average speedup factor of 93.77, while maintaining an average approximation error of 2.15%; for approximate Sparse PCA algorithm, our method achieves an average speedup factor of 6.77 and an average approximation error of merely 0.37%.

The aim of this paper is to address the challenge of gradual domain adaptation within a class of manifold-constrained data distributions. In particular, we consider a sequence of $T\ge2$ data distributions $P_1,\ldots,P_T$ undergoing a gradual shift, where each pair of consecutive measures $P_i,P_{i+1}$ are close to each other in Wasserstein distance. We have a supervised dataset of size $n$ sampled from $P_0$, while for the subsequent distributions in the sequence, only unlabeled i.i.d. samples are available. Moreover, we assume that all distributions exhibit a known favorable attribute, such as (but not limited to) having intra-class soft/hard margins. In this context, we propose a methodology rooted in Distributionally Robust Optimization (DRO) with an adaptive Wasserstein radius. We theoretically show that this method guarantees the classification error across all $P_i$s can be suitably bounded. Our bounds rely on a newly introduced {\it {compatibility}} measure, which fully characterizes the error propagation dynamics along the sequence. Specifically, for inadequately constrained distributions, the error can exponentially escalate as we progress through the gradual shifts. Conversely, for appropriately constrained distributions, the error can be demonstrated to be linear or even entirely eradicated. We have substantiated our theoretical findings through several experimental results.

Random matrix theory has proven to be a valuable tool in analyzing the generalization of linear models. However, the generalization properties of even two-layer neural networks trained by gradient descent remain poorly understood. To understand the generalization performance of such networks, it is crucial to characterize the spectrum of the feature matrix at the hidden layer. Recent work has made progress in this direction by describing the spectrum after a single gradient step, revealing a spiked covariance structure. Y et, the generalization error for linear models with spiked covariances has not been previously determined. We derive their generalization error in the asymptotic proportional regime. Our analysis demonstrates that the eigenvector and eigenvalue corresponding to the spike significantly influence the generalization error. Significant theoretical work has been dedicated to understanding generalization in linear regression models (Dobriban & Wager, 2018; Advani et al., 2020; Mel & Ganguli, 2021; Derezinski et al., 2020; Hastie et al., 2022; Kausik et al., 2024; Wang et al., 2024a). For the random features approximation, the first layer of the neural network is considered fixed, and only the outer layer is trained. It has been shown that to understand the generalization, we need to analyze the distribution of singular values of F . Works such as Pennington & Worah (2017); Adlam et al. (2019); Benigni & Péché (2021); Fan & Wang (2020); Wang & Zhu (2024); Péché (2019); Piccolo & Schröder (2021) have studied the spectrum of F in the asymptotic limit, enabling us to understand the generalization. However, random feature models do not leverage the feature learning capabilities of neural networks. To gain further insights into the performance of two-layer neural networks and their feature learning capabilities, we need to train the inner layer. Recent studies such as Ba et al. (2022); Moniri et al. (2023) have examined the effects on F of taking one gradient step for the inner layer. Specifically, Ba et al. (2022) showed that with a sufficiently large step size η, two-layer models can already outperform random feature models after just one step. Moniri et al. (2023) extended this work to study many different scales for the step size. The bulk corresponds to F 0, while the spikes represent the effect of P .

This paper presents a canonical polyadic (CP) tensor decomposition that addresses unaligned observations. The mode with unaligned observations is represented using functions in a reproducing kernel Hilbert space (RKHS). We introduce a versatile loss function that effectively accounts for various types of data, including binary, integer-valued, and positive-valued types. Additionally, we propose an optimization algorithm for computing tensor decompositions with unaligned observations, along with a stochastic gradient method to enhance computational efficiency. A sketching algorithm is also introduced to further improve efficiency when using the $\ell_2$ loss function. To demonstrate the efficacy of our methods, we provide illustrative examples using both synthetic data and an early childhood human microbiome dataset.