Recently, a tensor-on-tensor (ToT) regression model has been proposed to generalize tensor recovery, encompassing scenarios like scalar-on-tensor regression and tensor-on-vector regression. However, the exponential growth in tensor complexity poses challenges for storage and computation in ToT regression. To overcome this hurdle, tensor decompositions have been introduced, with the tensor train (TT)-based ToT model proving efficient in practice due to reduced memory requirements, enhanced computational efficiency, and decreased sampling complexity. Despite these practical benefits, a disparity exists between theoretical analysis and real-world performance. In this paper, we delve into the theoretical and algorithmic aspects of the TT-based ToT regression model. Assuming the regression operator satisfies the restricted isometry property (RIP), we conduct an error analysis for the solution to a constrained least-squares optimization problem. This analysis includes upper error bound and minimax lower bound, revealing that such error bounds polynomially depend on the order $N+M$. To efficiently find solutions meeting such error bounds, we propose two optimization algorithms: the iterative hard thresholding (IHT) algorithm (employing gradient descent with TT-singular value decomposition (TT-SVD)) and the factorization approach using the Riemannian gradient descent (RGD) algorithm. When RIP is satisfied, spectral initialization facilitates proper initialization, and we establish the linear convergence rate of both IHT and RGD.

In the grain industry, the identification of seed purity is a crucial task as it is an important factor in evaluating the quality of seeds. For rice seeds, this property allows for the reduction of unexpected influences of other varieties on rice yield, nutrient composition, and price. However, in practice, they are often mixed with seeds from others. This study proposes a novel method for automatically identifying the rice seed purity of a certain rice variety based on hybrid machine learning algorithms. The main idea is to use deep learning architectures for extracting important features from the raw data and then use machine learning algorithms for classification. Several experiments are conducted following a practical implementation to evaluate the performance of the proposed model. The obtained results show that the novel method improves significantly the performance of existing methods. Thus, it can be applied to design effective identification systems for rice seed purity.

We study the convergence of recursive regularized learning algorithms in the reproducing kernel Hilbert space (RKHS) with dependent and non-stationary online data streams. Firstly, we study the mean square asymptotic stability of a class of random difference equations in RKHS, whose non-homogeneous terms are martingale difference sequences dependent on the homogeneous ones. Secondly, we introduce the concept of random Tikhonov regularization path, and show that if the regularization path is slowly time-varying in some sense, then the output of the algorithm is consistent with the regularization path in mean square. Furthermore, if the data streams also satisfy the RKHS persistence of excitation condition, i.e. there exists a fixed length of time period, such that the conditional expectation of the operators induced by the input data accumulated over every time period has a uniformly strictly positive compact lower bound in the sense of the operator order with respect to time, then the output of the algorithm is consistent with the unknown function in mean square. Finally, for the case with independent and non-identically distributed data streams, the algorithm achieves the mean square consistency provided the marginal probability measures induced by the input data are slowly time-varying and the average measure over each fixed-length time period has a uniformly strictly positive lower bound.

It has recently been conjectured that neural network solution sets reachable via stochastic gradient descent (SGD) are convex, considering permutation invariances (Entezari et al., 2022). This means that a linear path can connect two independent solutions with low loss, given the weights of one of the models are appropriately permuted. However, current methods to test this theory often require very wide networks to succeed. In this work, we conjecture that more generally, the SGD solution set is a "star domain" that contains a "star model" that is linearly connected to all the other solutions via paths with low loss values, modulo permutations. We propose the Starlight algorithm that finds a star model of a given learning task. We validate our claim by showing that this star model is linearly connected with other independently found solutions. As an additional benefit of our study, we demonstrate better uncertainty estimates on the Bayesian Model Averaging over the obtained star domain. Further, we demonstrate star models as potential substitutes for model ensembles. Our code is available at https://github.com/aktsonthalia/starlight.

Embedding as a Service (EaaS) has become a widely adopted solution, which offers feature extraction capabilities for addressing various downstream tasks in Natural Language Processing (NLP). Prior studies have shown that EaaS can be prone to model extraction attacks; nevertheless, this concern could be mitigated by adding backdoor watermarks to the text embeddings and subsequently verifying the attack models post-publication. Through the analysis of the recent watermarking strategy for EaaS, EmbMarker, we design a novel CSE (Clustering, Selection, Elimination) attack that removes the backdoor watermark while maintaining the high utility of embeddings, indicating that the previous watermarking approach can be breached. In response to this new threat, we propose a new protocol to make the removal of watermarks more challenging by incorporating multiple possible watermark directions. Our defense approach, WARDEN, notably increases the stealthiness of watermarks and has been empirically shown to be effective against CSE attack.

While overparameterization in machine learning models offers great benefits in terms of optimization and generalization, it also leads to increased computational requirements as model sizes grow. In this work, we show that by leveraging the inherent low-dimensional structures of data and compressible dynamics within the model parameters, we can reap the benefits of overparameterization without the computational burdens. In practice, we demonstrate the effectiveness of this approach for deep low-rank matrix completion as well as fine-tuning language models. Our approach is grounded in theoretical findings for deep overparameterized low-rank matrix recovery, where we show that the learning dynamics of each weight matrix are confined to an invariant low-dimensional subspace. Consequently, we can construct and train compact, highly compressed factorizations possessing the same benefits as their overparameterized counterparts. In the context of deep matrix completion, our technique substantially improves training efficiency while retaining the advantages of overparameterization. For language model fine-tuning, we propose a method called "Deep LoRA", which improves the existing low-rank adaptation (LoRA) technique, leading to reduced overfitting and a simplified hyperparameter setup, while maintaining comparable efficiency. We validate the effectiveness of Deep LoRA on natural language tasks, particularly when fine-tuning with limited data. Our code is available at https://github.com/cjyaras/deep-lora-transformers.

Recent studies on online reinforcement learning (RL) have demonstrated the advantages of learning multiple behaviors from a single task, as in the case of few-shot adaptation to a new environment. Although this approach is expected to yield similar benefits in offline RL, appropriate methods for learning multiple solutions have not been fully investigated in previous studies. In this study, we therefore addressed the problem of finding multiple solutions from a single task in offline RL. We propose algorithms that can learn multiple solutions in offline RL, and empirically investigate their performance. Our experimental results show that the proposed algorithm learns multiple qualitatively and quantitatively distinctive solutions in offline RL.

Adaptive Risk Control (ARC) is an online calibration strategy based on set prediction that offers worst-case deterministic long-term risk control, as well as statistical marginal coverage guarantees. ARC adjusts the size of the prediction set by varying a single scalar threshold based on feedback from past decisions. In this work, we introduce Localized Adaptive Risk Control (L-ARC), an online calibration scheme that targets statistical localized risk guarantees ranging from conditional risk to marginal risk, while preserving the worst-case performance of ARC. L-ARC updates a threshold function within a reproducing kernel Hilbert space (RKHS), with the kernel determining the level of localization of the statistical risk guarantee. The theoretical results highlight a trade-off between localization of the statistical risk and convergence speed to the long-term risk target. Thanks to localization, L-ARC is demonstrated via experiments to produce prediction sets with risk guarantees across different data subpopulations, significantly improving the fairness of the calibrated model for tasks such as image segmentation and beam selection in wireless networks.

We address a core problem in causal inference: estimating heterogeneous treatment effects using panel data with general treatment patterns. Many existing methods either do not utilize the potential underlying structure in panel data or have limitations in the allowable treatment patterns. In this work, we propose and evaluate a new method that first partitions observations into disjoint clusters with similar treatment effects using a regression tree, and then leverages the (assumed) low-rank structure of the panel data to estimate the average treatment effect for each cluster. Our theoretical results establish the convergence of the resulting estimates to the true treatment effects. Computation experiments with semi-synthetic data show that our method achieves superior accuracy compared to alternative approaches, using a regression tree with no more than 40 leaves. Hence, our method provides more accurate and interpretable estimates than alternative methods.

We present a theoretical analysis of the Elo rating system, a popular method for ranking skills of players in an online setting. In particular, we study Elo under the Bradley--Terry--Luce model and, using techniques from Markov chain theory, show that Elo learns the model parameters at a rate competitive with the state of the art. We apply our results to the problem of efficient tournament design and discuss a connection with the fastest-mixing Markov chain problem.