A classical ASR approach treats the process of generating speech as a noisy channel. In this framing, text is drawn from some distribution and statistically transformed into We present a noisy channel generative model speech audio; the speech recognition task is then to invert of two sequences, for example text and speech, this generative model to infer the text most likely to have which enables uncovering the association between given rise to a given speech waveform. This generative the two modalities when limited paired data is model of speech was historically successful (Baker, 1975; available. To address the intractability of the exact Jelinek, 1976; Rabiner, 1989), but has been superseded in model under a realistic data setup, we propose modern discriminative systems by directly modeling the a variational inference approximation. To train conditional distribution of text, given speech (Graves et al., this variational model with categorical data, we 2006; Amodei et al., 2016). The direct approach has the advantage propose a KL encoder loss approach which has of allowing limited modeling power to be solely devoted connections to the wake-sleep algorithm. Identifying to the task of interest, whereas the generative one can the joint or conditional distributions by only be extremely sensitive to faulty assumptions in the speech observing unpaired samples from the marginals is audio model despite the fact that this is not the primary only possible under certain conditions in the data object of interest. However the generative approach allows distribution and we discuss under what type of learning in a principled way from untranscribed speech conditional independence assumptions that might audio, something fundamentally impossible in the direct approach.

The Forster transform is a method of regularizing a dataset X (in particular, by placing it in radial isotropic position) while maintaining some of its essential properties. Forster transforms have been an essential tool in a diverse range of settings, including functional analysis [Bar98, GGdOW17], communication complexity [For02], coding theory [DSW17], mixed determinant/volume approximation [GS02], learning theory [HM13, HKLM20, DKT21, DPT21] and the Paulsen problem in frame theory [KLLR18, HM19]. The reader is referred to [AKS20] for a more detailed discussion. Known algorithms for computing (approximate) Forster transforms [HM13, AKS20, DKT21] rely on black-box convex optimization (e.g., the ellipsoid algorithm) and consequently have weakly polynomial runtimes. Here we study the question of whether Forster transforms can be computed in strongly polynomial time. We then leverage Forster transforms for the problem of PAC learning halfspaces (both in the realizable setting and in the presence of semi-random label noise). Intuitively speaking, a Forster transform is a mapping that turns a dataset into one with good anti-concentration properties.

Learning the distribution of a continuous or categorical response variable $\boldsymbol y$ given its covariates $\boldsymbol x$ is a fundamental problem in statistics and machine learning. Deep neural network-based supervised learning algorithms have made great progress in predicting the mean of $\boldsymbol y$ given $\boldsymbol x$, but they are often criticized for their ability to accurately capture the uncertainty of their predictions. In this paper, we introduce classification and regression diffusion (CARD) models, which combine a denoising diffusion-based conditional generative model and a pre-trained conditional mean estimator, to accurately predict the distribution of $\boldsymbol y$ given $\boldsymbol x$. We demonstrate the outstanding ability of CARD in conditional distribution prediction with both toy examples and real-world datasets, the experimental results on which show that CARD in general outperforms state-of-the-art methods, including Bayesian neural network-based ones that are designed for uncertainty estimation, especially when the conditional distribution of $\boldsymbol y$ given $\boldsymbol x$ is multi-modal. In addition, we utilize the stochastic nature of the generative model outputs to obtain a finer granularity in model confidence assessment at the instance level for classification tasks.

In this paper, we propose a novel primal-dual proximal splitting algorithm (PD-PSA), named BALPA, for the composite optimization problem with equality constraints, where the loss function consists of a smooth term and a nonsmooth term composed with a linear mapping. In BALPA, the dual update is designed as a proximal point for a time-varying quadratic function, which balances the implementation of primal and dual update and retains the proximity-induced feature of classic PD-PSAs. In addition, by this balance, BALPA eliminates the inefficiency of classic PD-PSAs for composite optimization problems in which the Euclidean norm of the linear mapping or the equality constraint mapping is large. Therefore, BALPA not only inherits the advantages of simple structure and easy implementation of classic PD-PSAs but also ensures a fast convergence when these norms are large. Moreover, we propose a stochastic version of BALPA (S-BALPA) and apply the developed BALPA to distributed optimization to devise a new distributed optimization algorithm. Furthermore, a comprehensive convergence analysis for BALPA and S-BALPA is conducted, respectively. Finally, numerical experiments demonstrate the efficiency of the proposed algorithms.

Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current learning methods based on the clean label assumptions may fail with noisy labels. Yet, class labels are often mislabeled at both instance-level and boundary-level in real-world datasets. In this work, we take the lead in solving the instance-level label noise by proposing a Point Noise-Adaptive Learning (PNAL) framework. Compared to noise-robust methods on image tasks, our framework is noise-rate blind, to cope with the spatially variant noise rate specific to point clouds. Specifically, we propose a point-wise confidence selection to obtain reliable labels from the historical predictions of each point. A cluster-wise label correction is proposed with a voting strategy to generate the best possible label by considering the neighbor correlations. To handle boundary-level label noise, we also propose a variant ``PNAL-boundary " with a progressive boundary label cleaning strategy. Extensive experiments demonstrate its effectiveness on both synthetic and real-world noisy datasets. Even with $60\%$ symmetric noise and high-level boundary noise, our framework significantly outperforms its baselines, and is comparable to the upper bound trained on completely clean data. Moreover, we cleaned the popular real-world dataset ScanNetV2 for rigorous experiment. Our code and data is available at https://github.com/pleaseconnectwifi/PNAL.

We study the learning dynamics of self-predictive learning for reinforcement learning, a family of algorithms that learn representations by minimizing the prediction error of their own future latent representations. Despite its recent empirical success, such algorithms have an apparent defect: trivial representations (such as constants) minimize the prediction error, yet it is obviously undesirable to converge to such solutions. Our central insight is that careful designs of the optimization dynamics are critical to learning meaningful representations. We identify that a faster paced optimization of the predictor and semi-gradient updates on the representation, are crucial to preventing the representation collapse. Then in an idealized setup, we show self-predictive learning dynamics carries out spectral decomposition on the state transition matrix, effectively capturing information of the transition dynamics. Building on the theoretical insights, we propose bidirectional self-predictive learning, a novel self-predictive algorithm that learns two representations simultaneously. We examine the robustness of our theoretical insights with a number of small-scale experiments and showcase the promise of the novel representation learning algorithm with large-scale experiments.

We developed a simulator to quantify the effect of changes in environmental parameters on plant growth in precision farming. Our approach combines the processing of plant images with deep convolutional neural networks (CNN), growth curve modeling, and machine learning. As a result, our system is able to predict growth rates based on environmental variables, which opens the door for the development of versatile reinforcement learning agents.

This paper proposes a new algorithm for an automatic variable selection procedure in High Dimensional Graphical Models. The algorithm selects the relevant variables for the node of interest on the basis of mutual information. Several contributions in literature have investigated the use of mutual information in selecting the appropriate number of relevant features in a large data-set, but most of them have focused on binary outcomes or required high computational effort. The algorithm here proposed overcomes these drawbacks as it is an extension of Chow and Liu's algorithm. Once, the probabilistic structure of a High Dimensional Graphical Model is determined via the said algorithm, the best path-step, including variables with the most explanatory/predictive power for a variable of interest, is determined via the computation of the entropy coefficient of determination. The latter, being based on the notion of (symmetric) Kullback-Leibler divergence, turns out to be closely connected to the mutual information of the involved variables. The application of the algorithm to a wide range of real-word and publicly data-sets has highlighted its potential and greater effectiveness compared to alternative extant methods.

Moving agents perceive streams of information, typically a mix of RGB images, depth and inertial measurements. Probabilistic generative models [1] are a principled way to formalise the synthesis of this data, and from these models inference can be derived through Bayes' rule. We focus on exactly such inference and target the agent states and the scene map, a problem known as simultaneous localisation and mapping (SLAM). We treat it as a posterior approximation for a given state-space model, such that the combination is useful for model-based control: the posterior inference serves as a state estimator and the predictive state-space model as a simulator with which to plan ahead [2]. To pave the way towards decision making, we believe an inference method should have: a compatible predictive model for both RGB-D images and 6-DoF dynamics; principled state and map uncertainty; real-time performance on commodity hardware; state-of-the-art localisation accuracy. We motivate these requirements further in appendix J. Prominent methods like LSD-SLAM [3], ORB-SLAM [4], DSO [5] have propelled visual SLAM forward, with heavy focus on large-scale localisation. The core of modern large-scale SLAM is maximum a-posteriori (MAP) smoothing in a probabilistic factor graph [6, 7]. At present this demands sparsity assumptions for computational feasibility, which obstructs the tight integration of dense maps and rendering.

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.