We revisit the classic signal-to-symbol barrier in light of the remarkable ability of deep neural networks to generate realistic synthetic data. DeepFakes and spoofing highlight the feebleness of the link between physical reality and its abstract representation, whether learned by a digital computer or a biological agent. Starting from a widely applicable definition of abstract concept, we show that standard feed-forward architectures cannot capture but trivial concepts, regardless of the number of weights and the amount of training data, despite being extremely effective classifiers. On the other hand, architectures that incorporate recursion can represent a significantly larger class of concepts, but may still be unable to learn them from a finite dataset. We qualitatively describe the class of concepts that can be "understood" by modern architectures trained with variants of stochastic gradient descent, using a (free energy) Lagrangian to measure information complexity. Even if a concept has been understood, however, a network has no means of communicating its understanding to an external agent, except through continuous interaction and validation. We then characterize physical objects as abstract concepts and use the previous analysis to show that physical objects can be encoded by finite architectures. However, to understand physical concepts, sensors must provide persistently exciting observations, for which the ability to control the data acquisition process is essential (active perception). The importance of control depends on the modality, benefiting visual more than acoustic or chemical perception. Finally, we conclude that binding physical entities to digital identities is possible in finite time with finite resources, solving in principle the signal-to-symbol barrier problem, but we highlight the need for continuous validation.

We consider the optimization problem of minimizing an objective functional, which admits a variational form and is defined over probability distributions on the constrained domain, which poses challenges to both theoretical analysis and algorithmic design. Inspired by the mirror descent algorithm for constrained optimization, we propose an iterative particle-based algorithm, named Mirrored Variational Transport (mirrorVT), extended from the Variational Transport framework [7] for dealing with the constrained domain. In particular, for each iteration, mirrorVT maps particles to an unconstrained dual domain induced by a mirror map and then approximately perform Wasserstein gradient descent on the manifold of distributions defined over the dual space by pushing particles. At the end of iteration, particles are mapped back to the original constrained domain. Through simulated experiments, we demonstrate the effectiveness of mirrorVT for minimizing the functionals over probability distributions on the simplex- and Euclidean ball-constrained domains. We also analyze its theoretical properties and characterize its convergence to the global minimum of the objective functional.

Stochastic gradient descent (SGD) algorithm is an effective learning strategy to build a latent factor analysis (LFA) model on a high-dimensional and incomplete (HDI) matrix. A particle swarm optimization (PSO) algorithm is commonly adopted to make an SGD-based LFA model's hyper-parameters, i.e, learning rate and regularization coefficient, self-adaptation. However, a standard PSO algorithm may suffer from accuracy loss caused by premature convergence. To address this issue, this paper incorporates more historical information into each particle's evolutionary process for avoiding premature convergence following the principle of a generalized-momentum (GM) method, thereby innovatively achieving a novel GM-incorporated PSO (GM-PSO). With it, a GM-PSO-based LFA (GMPL) model is further achieved to implement efficient self-adaptation of hyper-parameters. The experimental results on three HDI matrices demonstrate that the GMPL model achieves a higher prediction accuracy for missing data estimation in industrial applications.

In this paper, we propose SGEM, Stochastic Gradient with Energy and Momentum, to solve a large class of general non-convex stochastic optimization problems, based on the AEGD method that originated in the work [AEGD: Adaptive Gradient Descent with Energy. arXiv: 2010.05109]. SGEM incorporates both energy and momentum at the same time so as to inherit their dual advantages. We show that SGEM features an unconditional energy stability property, and derive energy-dependent convergence rates in the general nonconvex stochastic setting, as well as a regret bound in the online convex setting. A lower threshold for the energy variable is also provided. Our experimental results show that SGEM converges faster than AEGD and generalizes better or at least as well as SGDM in training some deep neural networks.

Dynamical systems theory has recently been applied in optimization to prove that gradient descent algorithms avoid so-called strict saddle points of the loss function. However, in many modern machine learning applications, the required regularity conditions are not satisfied. In particular, this is the case for rectified linear unit (ReLU) networks. In this paper, we prove a variant of the relevant dynamical systems result, a center-stable manifold theorem, in which we relax some of the regularity requirements. Then, we verify that shallow ReLU networks fit into the new framework. Building on a classification of critical points of the square integral loss of shallow ReLU networks measured against an affine target function, we deduce that gradient descent avoids most saddle points. We proceed to prove convergence to global minima if the initialization is sufficiently good, which is expressed by an explicit threshold on the limiting loss.

In transfer learning (Pan and Yang, 2009; Sugiyama and Kawanabe, 2012), an algorithm is provided with abundant data from a source domain and scarce or no data from a target domain, and aims to train a model that generalizes well on the target domain. A simple yet effective approach is to pretrain a model with the rich source data and then finetune the model with the available target data via, e.g., stochastic gradient descent (SGD) (see, e.g., Yosinski et al. (2014)). Despite its wide applicability in practice, the power and limitation of the pretraining-finetuning based transfer learning framework is not fully understood in theory. The focus of this work is to consider this issue in a specific transfer learning setup known as covariate shift (Pan and Yang, 2009; Sugiyama and Kawanabe, 2012), where the source and target distributions differ in their marginal distributions over the input, but coincide in their conditional distribution of the output given the input. Regarding the theory of learning with covariate shift, there exists a rich set of results (Ben-David et al., 2010; Germain et al., 2013; Mansour et al., 2009; Mohri and Muñoz Medina, 2012; Cortes and

Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Thus far, prior work mostly focused on optimizing their reconstruction performance. This work investigates INRs from a novel perspective, i.e., as a tool for image compression. To this end, we propose the first comprehensive compression pipeline based on INRs including quantization, quantization-aware retraining and entropy coding. Encoding with INRs, i.e. overfitting to a data sample, is typically orders of magnitude slower. To mitigate this drawback, we leverage meta-learned initializations based on MAML to reach the encoding in fewer gradient updates which also generally improves rate-distortion performance of INRs. We find that our approach to source compression with INRs vastly outperforms similar prior work, is competitive with common compression algorithms designed specifically for images and closes the gap to state-of-the-art learned approaches based on Rate-Distortion Autoencoders. Moreover, we provide an extensive ablation study on the importance of individual components of our method which we hope facilitates future research on this novel approach to image compression.

This paper aims at jointly addressing two seemly conflicting issues in federated learning: differential privacy (DP) and Byzantine-robustness, which are particularly challenging when the distributed data are non-i.i.d. (independent and identically distributed). The standard DP mechanisms add noise to the transmitted messages, and entangles with robust stochastic gradient aggregation to defend against Byzantine attacks. In this paper, we decouple the two issues via robust stochastic model aggregation, in the sense that our proposed DP mechanisms and the defense against Byzantine attacks have separated influence on the learning performance. Leveraging robust stochastic model aggregation, at each iteration, each worker calculates the difference between the local model and the global one, followed by sending the element-wise signs to the master node, which enables robustness to Byzantine attacks. Further, we design two DP mechanisms to perturb the uploaded signs for the purpose of privacy preservation, and prove that they are $(\epsilon,0)$-DP by exploiting the properties of noise distributions. With the tools of Moreau envelop and proximal point projection, we establish the convergence of the proposed algorithm when the cost function is nonconvex. We analyze the trade-off between privacy preservation and learning performance, and show that the influence of our proposed DP mechanisms is decoupled with that of robust stochastic model aggregation. Numerical experiments demonstrate the effectiveness of the proposed algorithm.

We perform quantum process tomography (QPT) for both discrete- and continuous-variable quantum systems by learning a process representation using Kraus operators. The Kraus form ensures that the reconstructed process is completely positive. To make the process trace-preserving, we use a constrained gradient-descent (GD) approach on the so-called Stiefel manifold during optimization to obtain the Kraus operators. Our ansatz uses a few Kraus operators to avoid direct estimation of large process matrices, e.g., the Choi matrix, for low-rank quantum processes. The GD-QPT matches the performance of both compressed-sensing (CS) and projected least-squares (PLS) QPT in benchmarks with two-qubit random processes, but shines by combining the best features of these two methods. Similar to CS (but unlike PLS), GD-QPT can reconstruct a process from just a small number of random measurements, and similar to PLS (but unlike CS) it also works for larger system sizes, up to at least five qubits. We envisage that the data-driven approach of GD-QPT can become a practical tool that greatly reduces the cost and computational effort for QPT in intermediate-scale quantum systems.

Recently, Stochastic Gradient Descent (SGD) and its variants have become the dominant methods in the large-scale optimization of machine learning (ML) problems. A variety of strategies have been proposed for tuning the step sizes, ranging from adaptive step sizes to heuristic methods to change the step size in each iteration. Also, momentum has been widely employed in ML tasks to accelerate the training process. Yet, there is a gap in our theoretical understanding of them. In this work, we start to close this gap by providing formal guarantees to a few heuristic optimization methods and proposing improved algorithms. First, we analyze a generalized version of the AdaGrad (Delayed AdaGrad) step sizes in both convex and non-convex settings, showing that these step sizes allow the algorithms to automatically adapt to the level of noise of the stochastic gradients. We show for the first time sufficient conditions for Delayed AdaGrad to achieve almost sure convergence of the gradients to zero. Moreover, we present a high probability analysis for Delayed AdaGrad and its momentum variant in the non-convex setting. Second, we analyze SGD with exponential and cosine step sizes, which are empirically successful but lack theoretical support. We provide the very first convergence guarantees for them in the smooth and non-convex setting, with and without the Polyak-{\L}ojasiewicz (PL) condition. We also show their good property of adaptivity to noise under the PL condition. Third, we study the last iterate of momentum methods. We prove the first lower bound in the convex setting for the last iterate of SGD with constant momentum. Moreover, we investigate a class of Follow-The-Regularized-Leader-based momentum algorithms with increasing momentum and shrinking updates. We show that their last iterate has optimal convergence for unconstrained convex stochastic optimization problems.