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

Safe reinforcement learning (Safe RL) refers to a class of techniques that aim to prevent RL algorithms from violating constraints in the process of decision-making and exploration during trial and error. In this paper, a novel model-free Safe RL algorithm, formulated based on the multi-objective policy optimization framework is introduced where the policy is optimized towards optimality and safety, simultaneously. The optimality is achieved by the environment reward function that is subsequently shaped using a safety critic. The advantage of the Safety Optimized RL (SORL) algorithm compared to the traditional Safe RL algorithms is that it omits the need to constrain the policy search space. This allows SORL to find a natural tradeoff between safety and optimality without compromising the performance in terms of either safety or optimality due to strict search space constraints. Through our theoretical analysis of SORL, we propose a condition for SORL's converged policy to guarantee safety and then use it to introduce an aggressiveness parameter that allows for fine-tuning the mentioned tradeoff. The experimental results obtained in seven different robotic environments indicate a considerable reduction in the number of safety violations along with higher, or competitive, policy returns, in comparison to six different state-of-the-art Safe RL methods. The results demonstrate the significant superiority of the proposed SORL algorithm in safety-critical applications.

Affine frequency division multiplexing (AFDM), tailored as a novel multicarrier technique utilizing chirp signals for high-mobility communications, exhibits marked advantages compared to traditional orthogonal frequency division multiplexing (OFDM). AFDM is based on the discrete affine Fourier transform (DAFT) with two modifiable parameters of the chirp signals, termed as the pre-chirp parameter and post-chirp parameter, respectively. These parameters can be fine-tuned to avoid overlapping channel paths with different delays or Doppler shifts, leading to performance enhancement especially for doubly dispersive channel. In this paper, we propose a novel AFDM structure with the pre-chirp index modulation (PIM) philosophy (AFDM-PIM), which can embed additional information bits into the pre-chirp parameter design for both spectral and energy efficiency enhancement. Specifically, we first demonstrate that the application of distinct pre-chirp parameters to various subcarriers in the AFDM modulation process maintains the orthogonality among these subcarriers. Then, different pre-chirp parameters are flexibly assigned to each AFDM subcarrier according to the incoming bits. By such arrangement, aside from classical phase/amplitude modulation, extra binary bits can be implicitly conveyed by the indices of selected pre-chirping parameters realizations without additional energy consumption. At the receiver, both a maximum likelihood (ML) detector and a reduced-complexity ML-minimum mean square error (ML-MMSE) detector are employed to recover the information bits. It has been shown via simulations that the proposed AFDM-PIM exhibits superior bit error rate (BER) performance compared to classical AFDM, OFDM and IM-aided OFDM algorithms.

Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to inform the reconstruction process through an attention-guided loss function. By leveraging advances in unsupervised object discovery, we obtain an attention map of the scene which we employ in the loss function to put increased emphasis on reconstructing relevant objects, thus effectively incentivizing the model to learn more object-focused representations without compromising the established masking strategy. Our evaluations show that our pre-trained models learn better latent representations than the vanilla MAE, demonstrated by improved linear probing and k-NN classification results on several benchmarks while at the same time making ViTs more robust against varying backgrounds.

Transformer-based models have significantly improved performance across a range of multimodal understanding tasks, such as visual question answering and action recognition. However, multimodal Transformers significantly suffer from a quadratic complexity of the multi-head attention with the input sequence length, especially as the number of modalities increases. To address this, we introduce Low-Cost Multimodal Transformer (LoCoMT), a novel multimodal attention mechanism that aims to reduce computational cost during training and inference with minimal performance loss. Specifically, by assigning different multimodal attention patterns to each attention head, LoCoMT can flexibly control multimodal signals and theoretically ensures a reduced computational cost compared to existing multimodal Transformer variants. Experimental results on two multimodal datasets, namely Audioset and MedVidCL demonstrate that LoCoMT not only reduces GFLOPs but also matches or even outperforms established models.

Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple tasks to the downstream target task to achieve performance improvements. However, current approaches typically either train adapters on individual tasks or distill shared knowledge from source tasks, failing to fully exploit task-specific knowledge and the correlation between source and target tasks. To overcome these limitations, we propose PEMT, a novel parameter-efficient fine-tuning framework based on multi-task transfer learning. PEMT extends the mixture-of-experts (MoE) framework to capture the transferable knowledge as a weighted combination of adapters trained on source tasks. These weights are determined by a gated unit, measuring the correlation between the target and each source task using task description prompt vectors. To fully exploit the task-specific knowledge, we also propose the Task Sparsity Loss to improve the sparsity of the gated unit. We conduct experiments on a broad range of tasks over 17 datasets. The experimental results demonstrate our PEMT yields stable improvements over full fine-tuning, and state-of-the-art PEFT and knowledge transferring methods on various tasks. The results highlight the effectiveness of our method which is capable of sufficiently exploiting the knowledge and correlation features across multiple tasks.

The current Poisson factor models often assume that the factors are unknown, which overlooks the explanatory potential of certain observable covariates. This study focuses on high dimensional settings, where the number of the count response variables and/or covariates can diverge as the sample size increases. A covariate-augmented overdispersed Poisson factor model is proposed to jointly perform a high-dimensional Poisson factor analysis and estimate a large coefficient matrix for overdispersed count data. A group of identifiability conditions are provided to theoretically guarantee computational identifiability. We incorporate the interdependence of both response variables and covariates by imposing a low-rank constraint on the large coefficient matrix. To address the computation challenges posed by nonlinearity, two high-dimensional latent matrices, and the low-rank constraint, we propose a novel variational estimation scheme that combines Laplace and Taylor approximations. We also develop a criterion based on a singular value ratio to determine the number of factors and the rank of the coefficient matrix. Comprehensive simulation studies demonstrate that the proposed method outperforms the state-of-the-art methods in estimation accuracy and computational efficiency. The practical merit of our method is demonstrated by an application to the CITE-seq dataset. A flexible implementation of our proposed method is available in the R package \emph{COAP}.

In the era of large language models (LLMs), efficient and accurate data retrieval has become increasingly crucial for the use of domain-specific or private data in the retrieval augmented generation (RAG). Neural graph databases (NGDBs) have emerged as a powerful paradigm that combines the strengths of graph databases (GDBs) and neural networks to enable efficient storage, retrieval, and analysis of graph-structured data which can be adaptively trained with LLMs. The usage of neural embedding storage and Complex neural logical Query Answering (CQA) provides NGDBs with generalization ability. When the graph is incomplete, by extracting latent patterns and representations, neural graph databases can fill gaps in the graph structure, revealing hidden relationships and enabling accurate query answering. Nevertheless, this capability comes with inherent trade-offs, as it introduces additional privacy risks to the domain-specific or private databases. Malicious attackers can infer more sensitive information in the database using well-designed queries such as from the answer sets of where Turing Award winners born before 1950 and after 1940 lived, the living places of Turing Award winner Hinton are probably exposed, although the living places may have been deleted in the training stage due to the privacy concerns. In this work, we propose a privacy-preserved neural graph database (P-NGDB) framework to alleviate the risks of privacy leakage in NGDBs. We introduce adversarial training techniques in the training stage to enforce the NGDBs to generate indistinguishable answers when queried with private information, enhancing the difficulty of inferring sensitive information through combinations of multiple innocuous queries.

In an attempt to show that the acceptance probability of a quantum query algorithm making $q$ queries can be well-approximated almost everywhere by a classical decision tree of depth $\leq \text{poly}(q)$, Aaronson and Ambainis proposed the following conjecture: let $f: \{ \pm 1\}^n \rightarrow [0,1]$ be a degree $d$ polynomial with variance $\geq \epsilon$. Then, there exists a coordinate of $f$ with influence $\geq \text{poly} (\epsilon, 1/d)$. We show that for any polynomial $f: \{ \pm 1\}^n \rightarrow [0,1]$ of degree $d$ $(d \geq 2)$ and variance $\text{Var}[f] \geq 1/d$, if $\rho$ denotes a random restriction with survival probability $\dfrac{\log(d)}{C_1 d}$, $$ \text{Pr} \left[f_{\rho} \text{ has a coordinate with influence} \geq \dfrac{\text{Var}[f]^2 }{d^{C_2}} \right] \geq \dfrac{\text{Var}[f] \log(d)}{50C_1 d}$$ where $C_1, C_2>0$ are universal constants. Thus, Aaronson-Ambainis conjecture is true for a non-negligible fraction of random restrictions of the given polynomial assuming its variance is not too low.

Existing Quantization-Aware Training (QAT) methods intensively depend on the complete labeled dataset or knowledge distillation to guarantee the performances toward Full Precision (FP) accuracies. However, empirical results show that QAT still has inferior results compared to its FP counterpart. One question is how to push QAT toward or even surpass FP performances. In this paper, we address this issue from a new perspective by injecting the vicinal data distribution information to improve the generalization performances of QAT effectively. We present a simple, novel, yet powerful method introducing an Consistency Regularization (CR) for QAT. Concretely, CR assumes that augmented samples should be consistent in the latent feature space. Our method generalizes well to different network architectures and various QAT methods. Extensive experiments demonstrate that our approach significantly outperforms the current state-of-the-art QAT methods and even FP counterparts.

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.