We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. This optimization problem is unstable when advantages are negative and the loss becomes non-convex. We stabilize it by rollout policy regularization, which reduces variance and arises from fitting a local reward-improving target distribution. We evaluate AdvantageFlow on image generation tasks with Stable Diffusion 3.5 Medium. It outperforms both Flow-GRPO and a state-of-the-art forward-process RL baseline based on negative-aware fine-tuning.

Offline reinforcement learning (RL) is a variant of RL where the policy is learned from a previously collected dataset of trajectories and rewards. In our work, we propose a practical approach to offline RL with large language models (LLMs). We recast the problem as reward-weighted fine-tuning, which can be solved using similar techniques to supervised fine-tuning (SFT). To showcase the value of our approach, we apply it to learning short-horizon question-answering policies of a fixed length, where the agent reasons about potential answers or asks clarifying questions. Our work stands in a stark contrast to state-of-the-art methods in this domain, based on SFT and direct preference optimization, which have additional hyper-parameters and do not directly optimize for rewards. We compare to them empirically, and report major gains in both optimized rewards and language quality.

The development of autonomous machine learning (ML) agents capable of end-to-end data science workflows represents a significant frontier in artificial intelligence. These agents must orchestrate complex sequences of data analysis, feature engineering, model selection, and hyperparameter optimization, tasks that require sophisticated planning and iteration. While recent work on building ML agents has explored using large language models (LLMs) for direct code generation, tool-augmented approaches offer greater modularity and reliability. However, existing tool-use benchmarks focus primarily on task-specific tool selection or argument extraction for tool invocation, failing to evaluate the sophisticated planning capabilities required for ML Agents. In this work, we introduce a comprehensive benchmark for evaluating tool-augmented ML agents using a curated set of 61 specialized tools and 15 tabular ML challenges from Kaggle. Our benchmark goes beyond traditional tool-use evaluation by incorporating an in-memory named object management, allowing agents to flexibly name, save, and retrieve intermediate results throughout the workflows. We demonstrate that standard ReAct-style approaches struggle to generate valid tool sequences for complex ML pipelines, and that tree search methods with LLM-based evaluation underperform due to inconsistent state scoring. To address these limitations, we propose two simple approaches: 1) using shaped deterministic rewards with structured textual feedback, and 2) decomposing the original problem into a sequence of sub-tasks, which significantly improves trajectory validity and task performance. Using GPT-4o, our approach improves over ReAct by 16.52 percentile positions, taking the median across all Kaggle challenges. We believe our work provides a foundation for developing more capable tool-augmented planning ML agents.

Large language models (LLMs) solve reasoning problems by first generating a rationale and then answering. We formalize reasoning as a latent variable model and derive a reward-based filtered expectation-maximization (FEM) objective for learning to reason. This view connects EM and modern reward-based optimization, and shows that the main challenge lies in designing a sampling distribution of rationales that justify correct answers. We instantiate and compare three sampling schemes: rejection sampling with a budget, self-taught reasoner (STaR), and prompt posterior sampling (PPS), which only keeps the rationalization stage of STaR that conditions on the correct answer in the prompt. We experiment with LLM-as-a-judge calibration and summarization from feedback tasks, where conditioning on the correct answer provides a strong guidance for generating rationales. Our experiments show the efficacy of PPS over other sampling schemes, and that the sampling scheme can have a significant impact on performance.

Text-to-image diffusion models excel in generating photo-realistic images but are hampered by slow processing times. Training-free retrieval-based acceleration methods, which leverage pre-generated "trajectories," have been introduced to address this. Yet, these methods often lack diversity and fidelity as they depend heavily on similarities to stored prompts. To address this, we present ReCON (Retrieving CONcepts), an innovative retrieval-based diffusion acceleration method that extracts visual "concepts" from prompts, forming a knowledge base that facilitates the creation of adaptable trajectories. Consequently, ReCON surpasses existing retrieval-based methods, producing high-fidelity images and reducing required Neural Function Evaluations (NFEs) by up to 40%. Extensive testing on MS-COCO, Pick-a-pick, and DiffusionDB datasets confirms that RECON consistently outperforms established methods across multiple metrics such as Pick Score, CLIP Score, and Aesthetics Score. A user study further indicates that 76% of images generated by ReCON are rated as the highest fidelity, outperforming two competing methods, a purely text-based retrieval and a noise similarity-based retrieval.

Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper we propose the first active learning framework to alleviate LLM hallucinations, reducing costly human annotations of hallucination needed. By measuring fine-grained hallucinations from errors in semantic frame, discourse and content verifiability in text summarization, we propose HAllucination Diversity-Aware Sampling (HADAS) to select diverse hallucinations for annotations in active learning for LLM finetuning. Extensive experiments on three datasets and different backbone models demonstrate advantages of our method in effectively and efficiently mitigating LLM hallucinations.

Several cloud-based applications, such as cloud gaming, rent servers to execute jobs which arrive in an online fashion. Each job has a resource demand and must be dispatched to a cloud server which has enough resources to execute the job, which departs after its completion. Under the `pay-as-you-go' billing model, the server rental cost is proportional to the total time that servers are actively running jobs. The problem of efficiently allocating a sequence of online jobs to servers without exceeding the resource capacity of any server while minimizing total server usage time can be modelled as a variant of the dynamic bin packing problem (DBP), called MinUsageTime DBP. In this work, we initiate the study of the problem with multi-dimensional resource demands (e.g. CPU/GPU usage, memory requirement, bandwidth usage, etc.), called MinUsageTime Dynamic Vector Bin Packing (DVBP). We study the competitive ratio (CR) of Any Fit packing algorithms for this problem. We show almost-tight bounds on the CR of three specific Any Fit packing algorithms, namely First Fit, Next Fit, and Move To Front. We prove that the CR of Move To Front is at most $(2\mu+1)d +1$, where $\mu$ is the ratio of the max/min item durations. For $d=1$, this significantly improves the previously known upper bound of $6\mu+7$ (Kamali & Lopez-Ortiz, 2015). We then prove the CR of First Fit and Next Fit are bounded by $(\mu+2)d+1$ and $2\mu d+1$, respectively. Next, we prove a lower bound of $(\mu+1)d$ on the CR of any Any Fit packing algorithm, an improved lower bound of $2\mu d$ for Next Fit, and a lower bound of $2\mu$ for Move To Front in the 1-D case. All our bounds improve or match the best-known bounds for the 1-D case. Finally, we experimentally study the average-case performance of these algorithms on randomly generated synthetic data, and observe that Move To Front outperforms other Any Fit packing algorithms.

The design and analysis of randomized experiments is fundamental to many areas, from the physical and social sciences to industrial settings. Regression adjustment is a popular technique to reduce the variance of estimates obtained from experiments, by utilizing information contained in auxiliary covariates. While there is a large literature within the statistics community studying various approaches to regression adjustment and their asymptotic properties, little focus has been given to approaches in the finite population setting with non-asymptotic accuracy bounds. Further, prior work typically assumes that an entire population is exposed to an experiment, whereas practitioners often seek to minimize the number of subjects exposed to an experiment, for ethical and pragmatic reasons. In this work, we study the problems of estimating the sample mean, individual treatment effects, and average treatment effect with regression adjustment. We propose approaches that use techniques from randomized numerical linear algebra to sample a subset of the population on which to perform an experiment. We give non-asymptotic accuracy bounds for our methods and demonstrate that they compare favorably with prior approaches.

There is increasing attention toward search indexes based on dense vector representations as they can encode latent semantic features and can be generated efficiently, thanks to the advances in representation learning. Building an index on vectors was addressed by methods like locality-sensitive hashing (LSH), Inverted File Index (IVF), and near-neighbor graphs and perfected for high performance. However, the current near-neighbor (NN) indexes cannot be directly used in a real recommendation engine where both learned dense features and the constraints-attributes are used. The existing methods are cascaded index with vector search followed by a naive matching or inverted index for filtering on attribute tokens. This filtering on post-vector search matched sets often limits the control on output size and adds latency due to repeated calls to the NN engine. We aim to make a single-stage retrieval model that can retrieve in a single pass and control the output size without compromising on latency. An NN index amenable to this should have a very similar structure to the attribute token-based inverted index. Hence, we develop an efficient constraint search engine based on the high dimensional sparse embeddings of semantic features added with attribute tokens. With this, we get an Inverted index-based Constraint Near Neighbor search-ICONN, where we retrieve search results with 100% match on query attributes and close to its semantic features. We achieve a better latency vs recall10@10 tradeoff compared to the standard NN search followed by attribute filtering.

Vanilla federated learning does not support learning in an online environment, learning a personalized model on each client, and learning in a decentralized setting. There are existing methods extending federated learning in each of the three aspects. However, some important applications on enterprise edge servers (e.g. online item recommendation at global scale) involve the three aspects at the same time. Therefore, we propose a new learning setting Decentralized Personalized Online Federated Learning that considers all the three aspects at the same time.In this new setting for learning, the first technical challenge is how to aggregate the shared model parameters from neighboring clients to obtain a personalized local model with good performance on each client. We propose to directly learn an aggregation by optimizing the performance of the local model with respect to the aggregation weights. This not only improves personalization of each local model but also helps the local model adapting to potential data shift by intelligently incorporating the right amount of information from its neighbors. The second challenge is how to select the neighbors for each client. We propose a peer selection method based on the learned aggregation weights enabling each client to select the most helpful neighbors and reduce communication cost at the same time. We verify the effectiveness and robustness of our proposed method on three real-world item recommendation datasets and one air quality prediction dataset.

Many models for undirected graphs are based on factorizing the graph's adjacency matrix; these models find a vector representation of each node such that the predicted probability of a link between two nodes increases with the similarity (dot product) of their associated vectors. Recent work has shown that these models are unable to capture key structures in real-world graphs, particularly heterophilous structures, wherein links occur between dissimilar nodes. In contrast, a factorization with two vectors per node, based on logistic principal components analysis (LPCA), has been proven not only to represent such structures, but also to provide exact low-rank factorization of any graph with bounded max degree. However, this bound has limited applicability to real-world networks, which often have power law degree distributions with high max degree. Further, the LPCA model lacks interpretability since its asymmetric factorization does not reflect the undirectedness of the graph. We address these issues in two ways. First, we prove a new bound for the LPCA model in terms of arboricity rather than max degree; this greatly increases the bound's applicability to many sparse real-world networks. Second, we propose an alternative graph model whose factorization is symmetric and nonnegative, which allows for link predictions to be interpreted in terms of node clusters. We show that the bounds for exact representation in the LPCA model extend to our new model. On the empirical side, our model is optimized effectively on real-world graphs with gradient descent on a cross-entropy loss. We demonstrate its effectiveness on a variety of foundational tasks, such as community detection and link prediction.

Many models for graphs fall under the framework of edge-independent dot product models. These models output the probabilities of edges existing between all pairs of nodes, and the probability of a link between two nodes increases with the dot product of vectors associated with the nodes. Recent work has shown that these models are unable to capture key structures in real-world graphs, particularly heterophilous structures, wherein links occur between dissimilar nodes. We propose the first edge-independent graph generative model that is a) expressive enough to capture heterophily, b) produces nonnegative embeddings, which allow link predictions to be interpreted in terms of communities, and c) optimizes effectively on real-world graphs with gradient descent on a cross-entropy loss. Our theoretical results demonstrate the expressiveness of our model in its ability to exactly reconstruct a graph using a number of clusters that is linear in the maximum degree, along with its ability to capture both heterophily and homophily in the data. Further, our experiments demonstrate the effectiveness of our model for a variety of important application tasks such as multi-label clustering and link prediction.

Treatment effect estimation is a fundamental problem in causal inference. We focus on designing efficient randomized controlled trials, to accurately estimate the effect of some treatment on a population of $n$ individuals. In particular, we study sample-constrained treatment effect estimation, where we must select a subset of $s \ll n$ individuals from the population to experiment on. This subset must be further partitioned into treatment and control groups. Algorithms for partitioning the entire population into treatment and control groups, or for choosing a single representative subset, have been well-studied. The key challenge in our setting is jointly choosing a representative subset and a partition for that set. We focus on both individual and average treatment effect estimation, under a linear effects model. We give provably efficient experimental designs and corresponding estimators, by identifying connections to discrepancy minimization and leverage-score-based sampling used in randomized numerical linear algebra. Our theoretical results obtain a smooth transition to known guarantees when $s$ equals the population size. We also empirically demonstrate the performance of our algorithms.

There are various scenarios where very quick insights from a massive amount of data need to be extracted in a time-critical manner. These might be fresh insights or re-looking at why previous insights did not work and how to fix those. A marketing campaign is one real-world scenario where a non-programmer needs to dig such huge data in a very short period of time (a few hours) in order to hit a target revenue. In this demo paper, we will describe Electra - a system that integrates an automated data-insight discovery mechanism with a novel machine-learning (ML) driven approximate query processing (AQP) engine that can answer complex queries with a large number of predicates or conditions with high accuracy. This AQP engine uses a conditional generative model to generate a very small sample (~1000 rows) corresponding to the actual query to be answered and computes the highly accurate approximate answer from those instead of running the query against the original data. The insight discovery workflow bootstraps insights using ML algorithms based on the statistical characteristics of the data and further offers a no-code based interface to drill down for deeper insights. The queries from this interface are answered by the AQP engine that runs locally at the client-side itself to offer low latency interactions.

In this paper, we initiate the study of one-pass algorithms for solving the maximum-a-posteriori (MAP) inference problem for Non-symmetric Determinantal Point Processes (NDPPs). In particular, we formulate streaming and online versions of the problem and provide one-pass algorithms for solving these problems. In our streaming setting, data points arrive in an arbitrary order and the algorithms are constrained to use a single-pass over the data as well as sub-linear memory, and only need to output a valid solution at the end of the stream. Our online setting has an additional requirement of maintaining a valid solution at any point in time. We design new one-pass algorithms for these problems and show that they perform comparably to (or even better than) the offline greedy algorithm while using substantially lower memory.

In this paper, we introduce the online and streaming MAP inference and learning problems for Non-symmetric Determinantal Point Processes (NDPPs) where data points arrive in an arbitrary order and the algorithms are constrained to use a single-pass over the data as well as sub-linear memory. The online setting has an additional requirement of maintaining a valid solution at any point in time. For solving these new problems, we propose algorithms with theoretical guarantees, evaluate them on several real-world datasets, and show that they give comparable performance to state-of-the-art offline algorithms that store the entire data in memory and take multiple passes over it.

The goal of Approximate Query Processing (AQP) is to provide very fast but "accurate enough" results for costly aggregate queries thereby improving user experience in interactive exploration of large datasets. Recently proposed Machine-Learning-based AQP techniques can provide very low latency as query execution only involves model inference as compared to traditional query processing on database clusters. However, with increase in the number of filtering predicates (WHERE clauses), the approximation error significantly increases for these methods. Analysts often use queries with a large number of predicates for insights discovery. Thus, maintaining low approximation error is important to prevent analysts from drawing misleading conclusions. In this paper, we propose ELECTRA, a predicate-aware AQP system that can answer analytics-style queries with a large number of predicates with much smaller approximation errors. ELECTRA uses a conditional generative model that learns the conditional distribution of the data and at run-time generates a small (≈ 1000 rows) but representative sample, on which the query is executed to compute the approximate result. Our evaluations with four different baselines on three real-world datasets show that ELECTRA provides lower AQP error for large number of predicates compared to baselines.

e consider the experimental design problem in an online environment, an important practical task for reducing the variance of estimates in randomized experiments which allows for greater precision, and in turn, improved decision making. In this work, we present algorithms that build on recent advances in online discrepancy minimization which accommodate both arbitrary treatment probabilities and multiple treatments. The proposed algorithms are computational efficient, minimize covariate imbalance, and include randomization which enables robustness to misspecification. We provide worst case bounds on the expected mean squared error of the causal estimate and show that the proposed estimator is no worse than an implicit ridge regression, which are within a logarithmic factor of the best known results for offline experimental design. We conclude with a detailed simulation study showing favorable results relative to complete randomization as well as to offline methods for experimental design with time complexities exceeding our algorithm.

We give relative error coresets for training linear classifiers with a broad class of loss functions, including the logistic loss and hinge loss. Our construction achieves $(1\pm \epsilon)$ relative error with $\tilde O(d \cdot \mu_y(X)^2/\epsilon^2)$ points, where $\mu_y(X)$ is a natural complexity measure of the data matrix $X \in \mathbb{R}^{n \times d}$ and label vector $y \in \{-1,1\}^n$, introduced in by Munteanu et al. 2018. Our result is based on subsampling data points with probabilities proportional to their $\ell_1$ $Lewis$ $weights$. It significantly improves on existing theoretical bounds and performs well in practice, outperforming uniform subsampling along with other importance sampling methods. Our sampling distribution does not depend on the labels, so can be used for active learning. It also does not depend on the specific loss function, so a single coreset can be used in multiple training scenarios.

In this work, we reframe the problem of balanced treatment assignment as optimization of a two-sample test between test and control units. Using this lens we provide an assignment algorithm that is optimal with respect to the minimum spanning tree test of Friedman and Rafsky [1979]. This assignment to treatment groups may be performed exactly in polynomial time. We provide a probabilistic interpretation of this process in terms of the most probable element of designs drawn from a determinantal point process which admits a probabilistic interpretation of the design. We provide a novel formulation of estimation as transductive inference and show how the tree structures used in design can also be used in an adjustment estimator. We conclude with a simulation study demonstrating the improved efficacy of our method.