How can this training-evaluation gap be addressed? While specific techniques have been adopted to optimize certain confusion matrix based metrics, it is challenging or impossible in some cases to generalize the techniques to other metrics.

Accurately estimating nonlinear audio effects without access to paired input-output signals remains a challenging problem. This work studies unsupervised probabilistic approaches for solving this task. We introduce a method, novel for this application, based on diffusion generative models for blind system identification, enabling the estimation of unknown nonlinear effects using black- and gray-box models. This study compares this method with a previously proposed adversarial approach, analyzing the performance of both methods under different parameterizations of the effect operator and varying lengths of available effected recordings. Through experiments on guitar distortion effects, we show that the diffusion-based approach provides more stable results and is less sensitive to data availability, while the adversarial approach is superior at estimating more pronounced distortion effects. Our findings contribute to the robust unsupervised blind estimation of audio effects, demonstrating the potential of diffusion models for system identification in music technology.

How can this training-evaluation gap be addressed? While specific techniques have been adopted to optimize certain confusion matrix based metrics, it is challenging or impossible in some cases to generalize the techniques to other metrics.

Summary and Contributions: The paper proposes an adversarial minimax two player game approach for optimising the parameters of a generalised structural equation model (SEM) formulated as a saddle-point problem. The generalised SEM is defined in terms of a conditional expectation operator mapping between a hilbert space of structural functions of interest to a hilbert space of known or estimated functions of the outcome. These spaces are subsequently chosen to be the space of possible neural networks and a stochastic primal-dual algorithm is given for finding a solution to the saddle-point problem. Furthermore, the work proves global convergence of the algorithm. This main result is achieved, under certain specific data and weight initialisation conditions, using a regret analysis while considering the infinite width limit for neural networks that cause them to behave like linear learners.

In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging: autoregressive decoders can often explain the data without utilizing the latent space, known as posterior collapse. To mitigate this, state-of-the-art models weaken' thepowerful decoder' by applying uniformly random dropout to the decoder input.We show theoretically that this removes pointwise mutual information provided by the decoder input, which is compensated for by utilizing the latent space. We then propose an adversarial training strategy to achieve information-based stochastic dropout. Compared to uniform dropout on standard text benchmark datasets, our targeted approach increases both sequence modeling performance and the information captured in the latent space.

Structural equation models (SEMs) are widely used in sciences, ranging from economics to psychology, to uncover causal relationships underlying a complex system under consideration and estimate structural parameters of interest. We study estimation in a class of generalized SEMs where the object of interest is defined as the solution to a linear operator equation. We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using the stochastic gradient descent. We consider both 2-layer and multi-layer NNs with ReLU activation functions and prove global convergence in an overparametrized regime, where the number of neurons is diverging. The results are established using techniques from online learning and local linearization of NNs, and improve in several aspects the current state-of-the-art.

The paper proposes an adversarial approach to ordinal regression, building upon recent works along these lines for cost-sensitive losses. The proposed method is shown to be consistent, and to have favourable empirical performance compared to existing methods. The basic idea of the paper is simple yet interesting: since ordinal regression can be viewed as a type of multiclass classification, and the latter has recently been attacked by adversarial learning approaches with some success, one can combine the two to derive adversarial ordinal regression approaches. By itself this would make the contribution a little narrow, but it is further shown that the adversarial loss in this particular problem admits a tractable form (Thm 1), which allows for efficient optimisation. Fisher-consistency of the approach also follows as a consequence of existing results for the cost-sensitive case, which is a salient feature of the approach.

This paper proposes a method of improving upon existing meta-learning approaches by augmenting the training with a GAN setup. The basic idea has been explored in the context of semi-supervised learning: add an additional class to the classifier's outputs and train the classifier/discriminator to classify generated data as this additional fake class. This paper extends the reasoning for why it might work for semi supervised learning to why is might work for few-shot meta learning. The clarity of this paper could be greatly improved. They are presenting many different variants of few-shot learning in supervised and semi-supervised setting, and the notation is a bit tricky to follow initially.

Intelligent machine learning approaches are finding active use for event detection and identification that allow real-time situational awareness. Yet, such machine learning algorithms have been shown to be susceptible to adversarial attacks on the incoming telemetry data. This paper considers a physics-based modal decomposition method to extract features for event classification and focuses on interpretable classifiers including logistic regression and gradient boosting to distinguish two types of events: load loss and generation loss. The resulting classifiers are then tested against an adversarial algorithm to evaluate their robustness. The adversarial attack is tested in two settings: the white box setting, wherein the attacker knows exactly the classification model; and the gray box setting, wherein the attacker has access to historical data from the same network as was used to train the classifier, but does not know the classification model. Thorough experiments on the synthetic South Carolina 500-bus system highlight that a relatively simpler model such as logistic regression is more susceptible to adversarial attacks than gradient boosting.

This results in models which reduce storage limitations, have This paper introduces the Procedural (audio) Variational greater control and expressiveness, and have the capacity to autoEncoder (ProVE) framework as a general approach to create unique auditory experiences. PA models differ from learning Procedural Audio PA models of environmental physical modeling synthesis [3], which render sounds through sounds with an improvement to the realism of the synthesis simulations in computational physics. These physics-based while maintaining provision of control over the generated models can produce realistic and dynamic sounds, but are sound through adjustable parameters. The framework comprises computationally expensive and require a significant amount two stages: (i) Audio Class Representation, in which of domain knowledge to develop. On the other hand, PA a latent representation space is defined by training an audio models are simpler and more computationally efficient, using autoencoder, and (ii) Control Mapping, in which a joint algorithms to generate sound based on static and temporal function of static/temporal control variables derived from the control variables, usually accompanied by random noise audio and a random sample of uniform noise is learned to to span variations in synthesis. Despite its advantage in computational replace the audio encoder. We demonstrate the use of ProVE efficiency, current classical PA models still synthesize through the example of footstep sound effects on various sounds of lower quality compared to using real samples surfaces. Our results show that ProVE models outperform or physical modeling synthesis -- a primary reason why they both classical PA models and an adversarial-based approach are not yet in standard use in sound design [2, 4]. in terms of sound fidelity, as measured by Fréchet Audio The state-of-the-art for enhancing sound synthesis quality Distance (FAD), Maximum Mean Discrepancy (MMD), and involves data-driven neural audio synthesis, the subset of subjective evaluations, making them feasible tools for sound deep learning techniques for generative audio.