The inadequate mixing of conventional Markov Chain Monte Carlo (MCMC) methods for multi-modal distributions presents a significant challenge in practical applications such as Bayesian inference and molecular dynamics. Addressing this, we propose Diffusive Gibbs Sampling (DiGS), an innovative family of sampling methods designed for effective sampling from distributions characterized by distant and disconnected modes. DiGS integrates recent developments in diffusion models, leveraging Gaussian convolution to create an auxiliary noisy distribution that bridges isolated modes in the original space and applying Gibbs sampling to alternately draw samples from both spaces. Our approach exhibits a better mixing property for sampling multi-modal distributions than state-of-the-art methods such as parallel tempering. We demonstrate that our sampler attains substantially improved results across various tasks, including mixtures of Gaussians, Bayesian neural networks and molecular dynamics.
Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation such as data annotation and system assessment. Human perception and behaviour during human evaluation exhibit inherent variability due to diverse cognitive processes and subjective interpretations, which should be taken into account in modelling to better mimic the way people perceive and interact with the world. This paper introduces a novel meta-learning framework that treats HAS as a zero-shot density estimation problem, which incorporates human variability and allows for the efficient generation of human-like annotations for unlabelled test inputs. Under this framework, we propose two new model classes, conditional integer flows and conditional softmax flows, to account for ordinal and categorical annotations, respectively. The proposed method is evaluated on three real-world human evaluation tasks and shows superior capability and efficiency to predict the aggregated behaviours of human annotators, match the distribution of human annotations, and simulate the inter-annotator disagreements.
Dividing ads ranking system into retrieval, early, and final stages is a common practice in large scale ads recommendation to balance the efficiency and accuracy. The early stage ranking often uses efficient models to generate candidates out of a set of retrieved ads. The candidates are then fed into a more computationally intensive but accurate final stage ranking system to produce the final ads recommendation. As the early and final stage ranking use different features and model architectures because of system constraints, a serious ranking consistency issue arises where the early stage has a low ads recall, i.e., top ads in the final stage are ranked low in the early stage. In order to pass better ads from the early to the final stage ranking, we propose a multi-task learning framework for early stage ranking to capture multiple final stage ranking components (i.e. ads clicks and ads quality events) and their task relations. With our multi-task learning framework, we can not only achieve serving cost saving from the model consolidation, but also improve the ads recall and ranking consistency. In the online A/B testing, our framework achieves significantly higher click-through rate (CTR), conversion rate (CVR), total value and better ads-quality (e.g. reduced ads cross-out rate) in a large scale industrial ads ranking system.
This work extends the theory of identifiability in supervised learning by considering the consequences of having access to a distribution of tasks. In such cases, we show that identifiability is achievable even in the case of regression, extending prior work restricted to the single-task classification case. Furthermore, we show that the existence of a task distribution which defines a conditional prior over latent variables reduces the equivalence class for identifiability to permutations and scaling, a much stronger and more useful result. When we further assume a causal structure over these tasks, our approach enables simple maximum marginal likelihood optimization together with downstream applicability to causal representation learning. Empirically, we validate that our model outperforms more general unsupervised models in recovering canonical representations for synthetic and real-world data.
We examine the characteristic activation values of individual ReLU units in neural networks. We refer to the corresponding set for such characteristic activation values in the input space as the characteristic activation set of a ReLU unit. We draw an explicit connection between the characteristic activation set and learned features in ReLU networks. This connection leads to new insights into why various neural network normalization techniques used in modern deep learning architectures regularize and stabilize SGD optimization. Utilizing these insights, we propose a geometric approach to parameterize ReLU networks for improved feature learning. We empirically verify its usefulness with less carefully chosen initialization schemes and larger learning rates. We report improved optimization stability, faster convergence speed, and better generalization performance.
* 16 pages, 4 figures, 3 tables. Preprint, under review
We propose Adaptive Deep Kernel Fitting (ADKF), a general framework for learning deep kernels by interpolating between meta-learning and conventional learning. Our approach employs a bilevel optimization objective where we meta-learn feature representations that are generally useful across tasks, in the sense that task-specific Gaussian process models estimated on top of such features achieve the lowest possible predictive loss on average across tasks. We solve the resulting nested optimization problem using the implicit function theorem. We show that ADKF contains Deep Kernel Learning and Deep Kernel Transfer as special cases. Although ADKF is a completely general method, we argue that it is especially well-suited for drug discovery problems and demonstrate that it significantly outperforms previous state-of-the-art methods on a variety of real-world few-shot molecular property prediction tasks and out-of-domain molecular optimization tasks.
It is well understood that client-master communication can be a primary bottleneck in Federated Learning. In this work, we address this issue with a novel client subsampling scheme, where we restrict the number of clients allowed to communicate their updates back to the master node. In each communication round, all participated clients compute their updates, but only the ones with "important" updates communicate back to the master. We show that importance can be measured using only the norm of the update and we give a formula for optimal client participation. This formula minimizes the distance between the full update, where all clients participate, and our limited update, where the number of participating clients is restricted. In addition, we provide a simple algorithm that approximates the optimal formula for client participation which only requires secure aggregation and thus does not compromise client privacy. We show both theoretically and empirically that our approach leads to superior performance for Distributed SGD (DSGD) and Federated Averaging (FedAvg) compared to the baseline where participating clients are sampled uniformly. Finally, our approach is orthogonal to and compatible with existing methods for reducing communication overhead, such as local methods and communication compression methods.
With the advent of deep learning, neural network-based recommendation models have emerged as an important tool for tackling personalization and recommendation tasks. These networks differ significantly from other deep learning networks due to their need to handle categorical features and are not well studied or understood. In this paper, we develop a state-of-the-art deep learning recommendation model (DLRM) and provide its implementation in both PyTorch and Caffe2 frameworks. In addition, we design a specialized parallelization scheme utilizing model parallelism on the embedding tables to mitigate memory constraints while exploiting data parallelism to scale-out compute from the fully-connected layers. We compare DLRM against existing recommendation models and characterize its performance on the Big Basin AI platform, demonstrating its usefulness as a benchmark for future algorithmic experimentation and system co-design.
Time series classification (TSC), the problem of predicting class labels of time series, has been around for decades within the community of data mining and machine learning, and found many important applications such as biomedical engineering and clinical prediction. However, it still remains challenging and falls short of classification accuracy and efficiency. Traditional approaches typically involve extracting discriminative features from the original time series using dynamic time warping (DTW) or shapelet transformation, based on which an off-the-shelf classifier can be applied. These methods are ad-hoc and separate the feature extraction part with the classification part, which limits their accuracy performance. Plus, most existing methods fail to take into account the fact that time series often have features at different time scales. To address these problems, we propose a novel end-to-end neural network model, Multi-Scale Convolutional Neural Networks (MCNN), which incorporates feature extraction and classification in a single framework. Leveraging a novel multi-branch layer and learnable convolutional layers, MCNN automatically extracts features at different scales and frequencies, leading to superior feature representation. MCNN is also computationally efficient, as it naturally leverages GPU computing. We conduct comprehensive empirical evaluation with various existing methods on a large number of benchmark datasets, and show that MCNN advances the state-of-the-art by achieving superior accuracy performance than other leading methods.
Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as model sizes increase, so do the storage and memory requirements of the classifiers. We present a novel network architecture, Frequency-Sensitive Hashed Nets (FreshNets), which exploits inherent redundancy in both convolutional layers and fully-connected layers of a deep learning model, leading to dramatic savings in memory and storage consumption. Based on the key observation that the weights of learned convolutional filters are typically smooth and low-frequency, we first convert filter weights to the frequency domain with a discrete cosine transform (DCT) and use a low-cost hash function to randomly group frequency parameters into hash buckets. All parameters assigned the same hash bucket share a single value learned with standard back-propagation. To further reduce model size we allocate fewer hash buckets to high-frequency components, which are generally less important. We evaluate FreshNets on eight data sets, and show that it leads to drastically better compressed performance than several relevant baselines.