亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Zeroth-order (ZO) optimization has become a popular technique for solving machine learning (ML) problems when first-order (FO) information is difficult or impossible to obtain. However, the scalability of ZO optimization remains an open problem: Its use has primarily been limited to relatively small-scale ML problems, such as sample-wise adversarial attack generation. To our best knowledge, no prior work has demonstrated the effectiveness of ZO optimization in training deep neural networks (DNNs) without a significant decrease in performance. To overcome this roadblock, we develop DeepZero, a principled ZO deep learning (DL) framework that can scale ZO optimization to DNN training from scratch through three primary innovations. First, we demonstrate the advantages of coordinatewise gradient estimation (CGE) over randomized vector-wise gradient estimation in training accuracy and computational efficiency. Second, we propose a sparsityinduced ZO training protocol that extends the model pruning methodology using only finite differences to explore and exploit the sparse DL prior in CGE. Third, we develop the methods of feature reuse and forward parallelization to advance the practical implementations of ZO training. Our extensive experiments show that DeepZero achieves state-of-the-art (SOTA) accuracy on ResNet-20 trained on CIFAR-10, approaching FO training performance for the first time. Furthermore, we show the practical utility of DeepZero in applications of certified adversarial defense and DL-based partial differential equation error correction, achieving 10-20% improvement over SOTA. We believe our results will inspire future research on scalable ZO optimization and contribute to advancing DL with black box. Codes are available at //github.com/OPTML-Group/DeepZero.

The two-alternative forced choice (2AFC) experimental setup is popular in the visual perception literature, where practitioners aim to understand how human observers perceive distances within triplets that consist of a reference image and two distorted versions of that image. In the past, this had been conducted in controlled environments, with a tournament-style algorithm dictating which images are shown to each participant to rank the distorted images. Recently, crowd-sourced perceptual datasets have emerged, with no images shared between triplets, making ranking impossible. Evaluating perceptual distances using this data is non-trivial, relying on reducing the collection of judgements on a triplet to a binary decision -- which is suboptimal and prone to misleading conclusions. Instead, we statistically model the underlying decision-making process during 2AFC experiments using a binomial distribution. We use maximum likelihood estimation to fit a distribution to the perceptual judgements, conditioned on the perceptual distance to test and impose consistency and smoothness between our empirical estimates of the density. This way, we can evaluate a different number of judgements per triplet, and can calculate metrics such as likelihoods of judgements according to a set of distances -- key ingredients that neural network counterparts lack.

We propose EmoDistill, a novel speech emotion recognition (SER) framework that leverages cross-modal knowledge distillation during training to learn strong linguistic and prosodic representations of emotion from speech. During inference, our method only uses a stream of speech signals to perform unimodal SER thus reducing computation overhead and avoiding run-time transcription and prosodic feature extraction errors. During training, our method distills information at both embedding and logit levels from a pair of pre-trained Prosodic and Linguistic teachers that are fine-tuned for SER. Experiments on the IEMOCAP benchmark demonstrate that our method outperforms other unimodal and multimodal techniques by a considerable margin, and achieves state-of-the-art performance of 77.49% unweighted accuracy and 78.91% weighted accuracy. Detailed ablation studies demonstrate the impact of each component of our method.

Foundation models, such as Large language Models (LLMs), have attracted significant amount of interest due to their large number of applications. Existing works show that appropriate prompt design, such as Chain-of-Thoughts, can unlock LLM's powerful capacity in diverse areas. However, when handling tasks involving repetitive sub-tasks and/or deceptive contents, such as arithmetic calculation and article-level fake news detection, existing prompting strategies either suffers from insufficient expressive power or intermediate errors triggered by hallucination. To make LLM more discerning to such intermediate errors, we propose to guide LLM with a Divide-and-Conquer program that simultaneously ensures superior expressive power and disentangles task decomposition, sub-task resolution, and resolution assembly process. Theoretic analysis reveals that our strategy can guide LLM to extend the expressive power of fixed-depth Transformer. Experiments indicate that our proposed method can achieve better performance than typical prompting strategies in tasks bothered by intermediate errors and deceptive contents, such as large integer multiplication, hallucination detection and misinformation detection.

We present variational inference with sequential sample-average approximation (VISA), a method for approximate inference in computationally intensive models, such as those based on numerical simulations. VISA extends importance-weighted forward-KL variational inference by employing a sequence of sample-average approximations, which are considered valid inside a trust region. This makes it possible to reuse model evaluations across multiple gradient steps, thereby reducing computational cost. We perform experiments on high-dimensional Gaussians, Lotka-Volterra dynamics, and a Pickover attractor, which demonstrate that VISA can achieve comparable approximation accuracy to standard importance-weighted forward-KL variational inference with computational savings of a factor two or more for conservatively chosen learning rates.

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant compute compared to re-training. However, the distribution shift induced by new data typically results in degraded performance on previous data or poor adaptation to the new data. In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by final loss and language model (LM) evaluation benchmarks. Specifically, we show this for a weak but realistic distribution shift between two commonly used LLM pre-training datasets (English$\rightarrow$English) and a stronger distribution shift (English$\rightarrow$German) at the $405$M parameter model scale with large dataset sizes (hundreds of billions of tokens). Selecting the weak but realistic shift for larger-scale experiments, we also find that our continual learning strategies match the re-training baseline for a 10B parameter LLM. Our results demonstrate that LLMs can be successfully updated via simple and scalable continual learning strategies, matching the re-training baseline using only a fraction of the compute. Finally, inspired by previous work, we propose alternatives to the cosine learning rate schedule that help circumvent forgetting induced by LR re-warming and that are not bound to a fixed token budget.

To enable large-scale and efficient deployment of artificial intelligence (AI), the combination of AI and edge computing has spawned Edge Intelligence, which leverages the computing and communication capabilities of end devices and edge servers to process data closer to where it is generated. A key technology for edge intelligence is the privacy-protecting machine learning paradigm known as Federated Learning (FL), which enables data owners to train models without having to transfer raw data to third-party servers. However, FL networks are expected to involve thousands of heterogeneous distributed devices. As a result, communication efficiency remains a key bottleneck. To reduce node failures and device exits, a Hierarchical Federated Learning (HFL) framework is proposed, where a designated cluster leader supports the data owner through intermediate model aggregation. Therefore, based on the improvement of edge server resource utilization, this paper can effectively make up for the limitation of cache capacity. In order to mitigate the impact of soft clicks on the quality of user experience (QoE), the authors model the user QoE as a comprehensive system cost. To solve the formulaic problem, the authors propose a decentralized caching algorithm with federated deep reinforcement learning (DRL) and federated learning (FL), where multiple agents learn and make decisions independently

We consider a binary decision aggregation problem in the presence of both truthful and adversarial experts. The truthful experts will report their private signals truthfully with proper incentive, while the adversarial experts can report arbitrarily. The decision maker needs to design a robust aggregator to forecast the true state of the world based on the reports of experts. The decision maker does not know the specific information structure, which is a joint distribution of signals, states, and strategies of adversarial experts. We want to find the optimal aggregator minimizing regret under the worst information structure. The regret is defined by the difference in expected loss between the aggregator and a benchmark who makes the optimal decision given the joint distribution and reports of truthful experts. We prove that when the truthful experts are symmetric and adversarial experts are not too numerous, the truncated mean is optimal, which means that we remove some lowest reports and highest reports and take averaging among the left reports. Moreover, for many settings, the optimal aggregators are in the family of piecewise linear functions. The regret is independent of the total number of experts but only depends on the ratio of adversaries. We evaluate our aggregators by numerical experiment in an ensemble learning task. We also obtain some negative results for the aggregation problem with adversarial experts under some more general information structures and experts' report space.

Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis, thereby allowing manual manipulation in predicting the final answer.

High spectral dimensionality and the shortage of annotations make hyperspectral image (HSI) classification a challenging problem. Recent studies suggest that convolutional neural networks can learn discriminative spatial features, which play a paramount role in HSI interpretation. However, most of these methods ignore the distinctive spectral-spatial characteristic of hyperspectral data. In addition, a large amount of unlabeled data remains an unexploited gold mine for efficient data use. Therefore, we proposed an integration of generative adversarial networks (GANs) and probabilistic graphical models for HSI classification. Specifically, we used a spectral-spatial generator and a discriminator to identify land cover categories of hyperspectral cubes. Moreover, to take advantage of a large amount of unlabeled data, we adopted a conditional random field to refine the preliminary classification results generated by GANs. Experimental results obtained using two commonly studied datasets demonstrate that the proposed framework achieved encouraging classification accuracy using a small number of data for training.