Text-to-image generative models have recently attracted considerable interest, enabling the synthesis of high-quality images from textual prompts. However, these models often lack the capability to generate specific subjects from given reference images or to synthesize novel renditions under varying conditions. Methods like DreamBooth and Subject-driven Text-to-Image (SuTI) have made significant progress in this area. Yet, both approaches primarily focus on enhancing similarity to reference images and require expensive setups, often overlooking the need for efficient training and avoiding overfitting to the reference images. In this work, we present the $\lambda$-Harmonic reward function, which provides a reliable reward signal and enables early stopping for faster training and effective regularization.

Dataset Distillation is the task of synthesizing small datasets from large ones while still retaining comparable predictive accuracy to the original uncompressed dataset. Despite significant empirical progress in recent years, there is little understanding of the theoretical limitations/guarantees of dataset distillation, specifically, what excess risk is achieved by distillation compared to the original dataset, and how large are distilled datasets? In this work, we take a theoretical view on kernel ridge regression (KRR) based methods of dataset distillation such as Kernel Inducing Points. By transforming ridge regression in random Fourier features (RFF) space, we provide the first proof of the existence of small (size) distilled datasets and their corresponding excess risk for shift-invariant kernels. We prove that a small set of instances exists in the original input space such that its solution in the RFF space coincides with the solution of the original data. We further show that a KRR solution can be generated using this distilled set of instances which gives an approximation towards the KRR solution optimized on the full input data. The size of this set is linear in the dimension of the RFF space of the input set or alternatively near linear in the number of effective degrees of freedom, which is a function of the kernel, number of data points, and the regularization parameter $\lambda$. The error bound of this distilled set is also a function of $\lambda$. We verify our bounds analytically and empirically.

A common setting in multitask reinforcement learning (RL) demands that an agent rapidly adapt to various stationary reward functions randomly sampled from a fixed distribution. In such situations, the successor representation (SR) is a popular framework which supports rapid policy evaluation by decoupling a policy's expected discounted, cumulative state occupancies from a specific reward function. However, in the natural world, sequential tasks are rarely independent, and instead reflect shifting priorities based on the availability and subjective perception of rewarding stimuli. Reflecting this disjunction, in this paper we study the phenomenon of diminishing marginal utility and introduce a novel state representation, the $\lambda$ representation ($\lambda$R) which, surprisingly, is required for policy evaluation in this setting and which generalizes the SR as well as several other state representations from the literature. We establish the $\lambda$R's formal properties and examine its normative advantages in the context of machine learning, as well as its usefulness for studying natural behaviors, particularly foraging.

Distributional assumptions have been shown to be necessary for the robust learnability of concept classes when considering the exact-in-the-ball robust risk and access to random examples by Gourdeau et al. (2019). In this paper, we study learning models where the learner is given more power through the use of local queries, and give the first distribution-free algorithms that perform robust empirical risk minimization (ERM) for this notion of robustness. The first learning model we consider uses local membership queries (LMQ), where the learner can query the label of points near the training sample. We show that, under the uniform distribution, LMQs do not increase the robustness threshold of conjunctions and any superclass, e.g., decision lists and halfspaces. Faced with this negative result, we introduce the local equivalence query (LEQ) oracle, which returns whether the hypothesis and target concept agree in the perturbation region around a point in the training sample, as well as a counterexample if it exists. We show a separation result: on one hand, if the query radius $\lambda$ is strictly smaller than the adversary's perturbation budget $\rho$, then distribution-free robust learning is impossible for a wide variety of concept classes; on the other hand, the setting $\lambda=\rho$ allows us to develop robust ERM algorithms. We then bound the query complexity of these algorithms based on online learning guarantees and further improve these bounds for the special case of conjunctions. We finish by giving robust learning algorithms for halfspaces with margins on both $\{0,1\}^n$ and $\mathbb{R}^n$.

Studying conditional independence among many variables with few observations is a challenging task.Gaussian Graphical Models (GGMs) tackle this problem by encouraging sparsity in the precision matrix through $l_q$ regularization with $q\leq1$.However, most GMMs rely on the $l_1$ norm because the objective is highly non-convex for sub-$l_1$ pseudo-norms.In the frequentist formulation, the $l_1$ norm relaxation provides the solution path as a function of the shrinkage parameter $\lambda$.In the Bayesian formulation, sparsity is instead encouraged through a Laplace prior, but posterior inference for different $\lambda$ requires repeated runs of expensive Gibbs samplers.Here we propose a general framework for variational inference with matrix-variate Normalizing Flow in GGMs, which unifies the benefits of frequentist and Bayesian frameworks.As a key improvement on previous work, we train with one flow a continuum of sparse regression models jointly for all regularization parameters $\lambda$ and all $l_q$ norms, including non-convex sub-$l_1$ pseudo-norms.Within one model we thus have access to (i) the evolution of the posterior for any $\lambda$ and any $l_q$ (pseudo-) norm, (ii) the marginal log-likelihood for model selection, and (iii) the frequentist solution paths through simulated annealing in the MAP limit.

We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in minimax regret bounds, we show that the eluder dimension d_{\text{elu}} - a measure of the complexity of the function class - plays a crucial role in variance-dependent bounds. We consider two types of adversary: (1) Weak adversary: The adversary sets the reward variance before observing the learner's action. In this setting, we prove that a regret of \Omega( \sqrt{ \min (A, d_{\text{elu}}) \Lambda } d_{\text{elu}}) is unavoidable when d_{\text{elu}} \leq \sqrt{A T}, where A is the number of actions, T is the total number of rounds, and \Lambda is the total variance over T rounds. For the A\leq d_{\text{elu}} regime, we derive a nearly matching upper bound \tilde{O}( \sqrt{ A\Lambda } d_{\text{elu} }) for the special case where the variance is revealed at the beginning of each round.

We investigate the entity alignment (EA) problem with unlabeled dangling cases, meaning that partial entities have no counterparts in the other knowledge graph (KG), yet these entities are unlabeled. The problem arises when the source and target graphs are of different scales, and it is much cheaper to label the matchable pairs than the dangling entities. To address this challenge, we propose the framework \textit{Lambda} for dangling detection and entity alignment. Lambda features a GNN-based encoder called KEESA with a spectral contrastive learning loss for EA and a positive-unlabeled learning algorithm called iPULE for dangling detection. Our dangling detection module offers theoretical guarantees of unbiasedness, uniform deviation bounds, and convergence.

Summary: the paper proposes a clustering method for linear dynamical systems, based on minimizing the kernalized norm between extended observability spaces. Since the objective function contains terms involving discrete Lypanunov equations (DLEs), the paper derives how to pass the derivatives through, yielding a gradient descent algorithm. Experiments are presented on 2 datasets, for LDS clustering and sparse codebook learning. Originality: 1) novelty: the paper is moderately novel, but fairly straightforward. The difference with other related works [3,9,10,11,12] in terms of objective functions, assumptions/constraints, canonical forms should be discussed more.

Depression is a globally prevalent mental disorder with potentially severe repercussions if not addressed, especially in individuals with recurrent episodes. Prior research has shown that early intervention has the potential to mitigate or alleviate symptoms of depression. However, implementing such interventions in a real-world setting may pose considerable challenges. A promising strategy involves leveraging machine learning and artificial intelligence to autonomously detect depression indicators from diverse data sources. One of the most widely available and informative data sources is text, which can reveal a person's mood, thoughts, and feelings. In this context, virtual agents programmed to conduct interviews using clinically validated questionnaires, such as those found in the DAIC-WOZ dataset, offer a robust means for depression detection through linguistic analysis. Utilizing BERT-based models, which are powerful and versatile yet use fewer resources than contemporary large language models, to convert text into numerical representations significantly enhances the precision of depression diagnosis. These models adeptly capture complex semantic and syntactic nuances, improving the detection accuracy of depressive symptoms. Given the inherent limitations of these models concerning text length, our study proposes text summarization as a preprocessing technique to diminish the length and intricacies of input texts. Implementing this method within our uniquely developed framework for feature extraction and classification yielded an F1-score of 0.67 on the test set surpassing all prior benchmarks and 0.81 on the validation set exceeding most previous results on the DAIC-WOZ dataset. Furthermore, we have devised a depression lexicon to assess summary quality and relevance. This lexicon constitutes a valuable asset for ongoing research in depression detection.

The idea of decision-aware model learning, that models should be accurate where it matters for decision-making, has gained prominence in model-based reinforcement learning. While promising theoretical results have been established, the empirical performance of algorithms leveraging a decision-aware loss has been lacking, especially in continuous control problems. In this paper, we present a study on the necessary components for decision-aware reinforcement learning models and we showcase design choices that enable well-performing algorithms. To this end, we provide a theoretical and empirical investigation into prominent algorithmic ideas in the field. We highlight that empirical design decisions established in the MuZero line of works are vital to achieving good performance for related algorithms, and we showcase differences in behavior between different instantiations of value-aware algorithms in stochastic environments. Using these insights, we propose the Latent Model-Based Decision-Aware Actor-Critic framework ($\lambda$-AC) for decision-aware model-based reinforcement learning in continuous state-spaces and highlight important design choices in different environments.