论文检索

Theory · Everything Else

Sabrina Herbst, Sandeep Cranganore, Vincenzo De Maio, Ivona Brandić

With the increasing interest in Quantum Machine Learning, Quantum Neural Networks (QNNs) have emerged and gained significant attention. These models have, however, been shown to be notoriously difficult to train, which we hypothesize is partially due to the architectures, called ansatzes, that are hardly studied at this point. Therefore, in this paper, we take a step back and analyze ansatzes. We initially consider their expressivity, i.e., the space of operations they are able to express, and show that the closeness to being a 2-design, the primarily used measure, fails at capturing this property. Hence, we look for alternative ways to characterize ansatzes, unrelated to expressivity, by considering the local neighborhood of the model space, in particular, analyzing model distinguishability upon small perturbation of parameters. We derive an upper bound on their distinguishability, showcasing that QNNs using the Hardware Efficient Ansatz with few parameters are hardly discriminable upon update. Our numerical experiments support our bounds and further indicate that there is a significant degree of variability, which stresses the need for warm-starting or clever initialization. Altogether, our work provides an ansatz-centric perspective on training dynamics and difficulties in QNNs, ultimately suggesting that iterative training of small quantum models may not be effective, which contrasts their initial motivation.

Probabilistic Methods · Everything Else

Yam Tawachi, Bracha Laufer-Goldshtein

Conformal prediction has attracted significant attention as a distribution-free method for uncertainty quantification in black-box models, providing prediction sets with guaranteed coverage. However, its practical utility is often limited when these prediction sets become excessively large, reducing its overall effectiveness. In this paper, we introduce a novel approach to conformal prediction for classification problems, which leverages a multi-dimensional nonconformity score. By extending standard conformal prediction to higher dimensions, we achieve better separation between correct and incorrect labels. Utilizing this we can focus on regions with low concentrations of incorrect labels, leading to smaller, more informative prediction sets. To efficiently generate the multi-dimensional score, we employ a self-ensembling technique that trains multiple diverse classification heads on top of a backbone model. We demonstrate the advantage of our approach compared to baselines across different benchmarks.

Optimization · Everything Else

Qiang Liu, Mengyu Chu, Nils Thuerey

The loss functions of many learning problems contain multiple additive terms that can disagree and yield conflicting update directions. For Physics-Informed Neural Networks (PINNs), loss terms on initial/boundary conditions and physics equations are particularly interesting as they are well-established as highly difficult tasks. To improve learning the challenging multi-objective task posed by PINNs, we propose the ConFIG method, which provides conflict-free updates by ensuring a positive dot product between the final update and each loss-specific gradient. It also maintains consistent optimization rates for all loss terms and dynamically adjusts gradient magnitudes based on conflict levels. We additionally leverage momentum to accelerate optimizations by alternating the back-propagation of different loss terms. We provide a mathematical proof showing the convergence of the ConFIG method, and it is evaluated across a range of challenging PINN scenarios. ConFIG consistently shows superior performance and runtime compared to baseline methods. We also test the proposed method in a classic multi-task benchmark, where the ConFIG method likewise exhibits a highly promising performance. Source code is available at https://tum-pbs.github.io/ConFIG

Deep Learning · Everything Else

Yury Gorishniy, Akim Kotelnikov, Artem Babenko

Deep learning architectures for supervised learning on tabular data range from simple multilayer perceptrons (MLP) to sophisticated Transformers and retrieval-augmented methods.This study highlights a major, yet so far overlooked opportunity for substantially improving tabular MLPs; namely, parameter-efficient ensembling -- a paradigm for imitating an ensemble of models with just one model.We start by describing TabM -- a simple model based on MLP and BatchEnsemble (an existing technique), improved with our custom modifications.Then, we perform a large scale evaluation of tabular DL architectures on public benchmarks in terms of both task performance and efficiency, which renders the landscape of tabular DL in a new light.In particular, we find that TabM outperforms prior tabular DL models, while the complexity of attention- and retrieval-based methods does not pay off.Lastly, we conduct a detailed empirical analysis, that sheds some light on the high performance of TabM.For example, we show that parameter-efficient ensembling is not an arbitrary trick, but rather a highly effective way to reduce overfitting and improve optimization dynamics of tabular MLPs.Overall, our work brings an impactful technique to tabular DL, analyses its behaviour, and advances the performance-efficiency tradeoff with TabM -- a simple and powerful baseline for researchers and practitioners.

Applications · Everything Else

Louis Bradshaw, Simon Colton

We introduce an extensive new dataset of MIDI files, created by transcribing audio recordings of piano performances into their constituent notes. The data pipeline we use is multi-stage, employing a language model to autonomously crawl and score audio recordings from the internet based on their metadata, followed by a stage of pruning and segmentation using an audio classifier. The resulting dataset contains over one million distinct MIDI files, comprising roughly 100,000 hours of transcribed audio. We provide an in-depth analysis of our techniques, offering statistical insights, and investigate the content by extracting metadata tags, which we also provide. Dataset available at https://github.com/loubbrad/aria-midi.

Theory · Everything Else

Ravindran Kannan, Chiranjib Bhattacharyya, Praneeth Kacham, David Woodruff

A central problem related to transformers can be stated as follows: given two $n \times d$ matrices $Q$ and $K$, and a non-negative function $f$, define the matrix $A$ as follows: (1) apply the function $f$ to each entry of the $n \times n$ matrix $Q K^T$, and then (2) normalize each of the row sums of $A$ to be equal to $1$. The matrix $A$ can be computed in $O(n^2 d)$ time assuming $f$ can be applied to a number in constant time, but the quadratic dependence on $n$ is prohibitive in applications where it corresponds to long context lengths. For a large class of functions $f$, we show how to find all the "large attention scores", i.e., entries of $A$ which are at least a positive value $\varepsilon$, in time with linear dependence on $n$ (i.e., $n \cdot \textrm{poly}(d/\varepsilon)$) for a positive parameter $\varepsilon > 0$. Our class of functions include all functions $f$ of the form $f(x) = |x|^p$, as explored recently in transformer models. Using recently developed tools from randomized numerical linear algebra, we prove that for any $K$, there is a "universal set" $U \subset [n]$ of size independent of $n$, such that for any $Q$ and any row $i$, the large attention scores $A_{i,j}$ in row $i$ of $A$ all have $j \in U$. We also find $U$ in $n \cdot \textrm{poly}(d/\varepsilon)$ time. Notably, we (1) make no assumptions on the data, (2) our workspace does not grow with $n$, and (3) our algorithms can be computed in streaming and parallel settings. We empirically show the benefits of our scheme for vision transformers, showing how to train new models that use our universal set while training as well, showing that our model is able to consistently select "important keys'" during training. We also provide theoretical motivation by formulating a planted model in which our efficient algorithms provably identify relevant keys for each query.

Optimization · Everything Else

Eduard Gorbunov, Nazarii Tupitsa, Sayantan Choudhury, Alen Aliev, Peter Richtarik, Samuel Horváth, Martin Takáč

Due to the non-smoothness of optimization problems in Machine Learning, generalized smoothness assumptions have been gaining a lot of attention in recent years. One of the most popular assumptions of this type is $(L_0,L_1)$-smoothness (Zhang et al., 2020). In this paper, we focus on the class of (strongly) convex $(L_0,L_1)$-smooth functions and derive new convergence guarantees for several existing methods. In particular, we derive improved convergence rates for Gradient Descent with (Smoothed) Gradient Clipping and for Gradient Descent with Polyak Stepsizes. In contrast to the existing results, our rates do not rely on the standard smoothness assumption and do not suffer from the exponential dependency on the initial distance to the solution. We also extend these results to the stochastic case under the over-parameterization assumption, propose a new accelerated method for convex $(L_0,L_1)$-smooth optimization, and derive new convergence rates for Adaptive Gradient Descent (Malitsky and Mishchenko, 2020).

Reinforcement Learning · Everything Else

Ziyu Liu, Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Haodong Duan, Conghui He, Yuanjun Xiong, Dahua Lin, Jiaqi Wang

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization algorithms like direct preference optimization (DPO).Existing visual alignment methods, primarily designed for single-image scenarios, struggle to effectively handle the complexity of multi-image tasks due to the scarcity of diverse training data and the high cost of annotating chosen/rejected pairs.We present Multi-Image Augmented Direct Preference Optimization (MIA-DPO), a visual preference alignment approach that effectively handles multi-image inputs.MIA-DPO mitigates the scarcity of diverse multi-image training data by extending single-image data with unrelated images arranged in grid collages or pic-in-pic formats, significantly reducing the costs associated with multi-image data annotations.Our observation reveals that attention values of LVLMs vary considerably across different images. We use attention values to identify and filter out rejected responses the model may have mistakenly focused on.Our attention-aware selection for constructing the chosen/rejected pairs without relying on (i) human annotation, (ii) extra data, and (iii) external models or APIs.MIA-DPO is compatible with various architectures and outperforms existing methods on five multi-image benchmarks, achieving an average performance boost of 3.0% on LLaVA-v1.5 and 4.3% on the recent InternLM-XC2.5.Moreover, MIA-DPO has a minimal effect on the model's ability to understand single images.

Social Aspects · Everything Else

Vibhhu Sharma, Bryan Wilder

Machine learning is increasingly used to select which individuals receive limited-resource interventions in domains such as human services, education, development, and more. However, it is often not apparent what the right quantity is for models to predict. In particular, policymakers rarely have access to data from a randomized controlled trial (RCT) that would enable accurate estimates of treatment effects -- which individuals would benefit more from the intervention. Observational data is more likely to be available, creating a substantial risk of bias in treatment effect estimates. Practitioners instead commonly use a technique termed "risk-based targeting" where the model is just used to predict each individual's status quo outcome (an easier, non-causal task). Those with higher predicted risk are offered treatment. There is currently almost no empirical evidence to inform which choices lead to the most effect machine learning-informed targeting strategies in social domains. In this work, we use data from 5 real-world RCTs in a variety of domains to empirically assess such choices. We find that when treatment effects can be estimated reliably (which we simulate by using direct outcome observations), treatment effect based targeting substantially outperforms risk-based targeting, even when treatment effect estimates are biased. Moreover, these results hold even when the policymaker has strong normative preferences for assisting higher-risk individuals. However, when treatment effects must be predicted from features alone (as is always the case in practice), performance can degrade significantly due to limited data making it difficult to learn accurate mappings from features to treatment effects. Our results suggest treatment effect targeting has significant potential benefits, but realizing these benefits requires careful attention to model training and validation.

Deep Learning · Everything Else

George Wang, Jesse Hoogland, Stan van Wingerden, Zach Furman, Daniel Murfet

We introduce refined variants of the Local Learning Coefficient (LLC), a measure of model complexity grounded in singular learning theory, to study the development of internal structure in transformer language models during training. By applying these refined LLCs (rLLCs) to individual components of a two-layer attention-only transformer, we gain novel insights into the progressive differentiation and specialization of attention heads. Our methodology reveals how attention heads differentiate into distinct functional roles over the course of training, analyzes the types of data these heads specialize to process, and discovers a previously unidentified multigram circuit. These findings demonstrate that rLLCs provide a principled, quantitative toolkit for developmental interpretability, which aims to understand models through their evolution across the learning process. This work advances the field of developmental interpretability by providing a mathematically rigorous approach to understanding neural networks through the lens of their learning process. More broadly, this work takes a step towards establishing the correspondence between data distributional structure, geometric properties of the loss landscape, learning dynamics, and emergent computational structures in neural networks.

Applications · Everything Else

Ezra Karger, Houtan Bastani, Chen Yueh-Han, Zachary Jacobs, Danny Halawi, Fred Zhang, Philip E. Tetlock

Forecasts of future events are essential inputs into informed decision-making. Machine learning (ML) systems have the potential to deliver forecasts at scale, but there is no framework for evaluating the accuracy of ML systems on a standardized set of forecasting questions. To address this gap, we introduce ForecastBench: a dynamic benchmark that evaluates the accuracy of ML systems on an automatically generated and regularly updated set of 1,000 forecasting questions. To avoid any possibility of data leakage, ForecastBench is comprised solely of questions about future events that have no known answer at the time of submission. We quantify the capabilities of current ML systems by collecting forecasts from expert (human) forecasters, the general public, and LLMs on a random subset of questions from the benchmark ($N=200$). While LLMs have achieved super-human performance on many benchmarks, they perform less well here: expert forecasters outperform the top-performing LLM ($p$-value $<0.001$). We display system and human scores in a public leaderboard at www.forecastbench.org.

Deep Learning · Everything Else

Simla Harma, Ayan Chakraborty, Elizaveta Kostenok, Danila Mishin, Dongho Ha, Babak Falsafi, Martin Jaggi, Ming Liu, Yunho Oh, Suvinay Subramanian 等

The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two prominent compression methods that have been shown to reduce DNNs' computational and memory footprints significantly while preserving model accuracy. However, how these two methods interact when combined together remains a key question for developers, as many tacitly assume that they are orthogonal, meaning that their combined use does not introduce additional errors beyond those introduced by each method independently. In this paper, we provide the first mathematical proof that sparsity and quantization are non-orthogonal. We corroborate these results with experiments spanning a range of large language models, including the OPT and LLaMA model families (with 125M to 8B parameters), and vision models like ViT and ResNet. We show that the order in which we apply these methods matters because applying quantization before sparsity may disrupt the relative importance of tensor elements, which may inadvertently remove significant elements from a tensor. More importantly, we show that even if applied in the correct order, the compounded errors from sparsity and quantization can significantly harm accuracy. Our findings extend to the efficient deployment of large models in resource-constrained compute platforms to reduce serving cost, offering insights into best practices for applying these compression methods to maximize hardware resource efficiency without compromising accuracy.

Optimization · Everything Else

Zeou Hu, Yaoliang Yu

Gradient-based multi-objective optimization (MOO) is essential in modern machine learning, with applications in e.g., multi-task learning, federated learning, algorithmic fairness and reinforcement learning. In this work, we first reveal some limitations of Pareto stationarity, a widely accepted first-order condition for Pareto optimality, in the presence of sparse function-variable structures. Next, to account for such sparsity, we propose a novel solution concept termed Refined Pareto Stationarity (RPS), which we prove is always sandwiched between Pareto optimality and Pareto stationarity. We give an efficient partitioning algorithm to automatically mine the function-variable dependency and substantially trim non-optimal Pareto stationary solutions. Then, we show that gradient-based descent algorithms in MOO can be enhanced with our refined partitioning. In particular, we propose Multiple Gradient Descent Algorithm with Refined Partition (RP-MGDA) as an example method that converges to RPS, while still enjoying a similar per-step complexity and convergence rate. Lastly, we validate our approach through experiments on both synthetic examples and realistic application scenarios where distinct function-variable dependency structures appear. Our results highlight the importance of exploiting function-variable structure in gradient-based MOO, and provide a seamless enhancement to existing approaches.

Social Aspects · Everything Else

Stephen Casper, David Krueger, Dylan Hadfield-Menell

Nations across the world are working to govern AI. However, from a technical perspective, the best way to do this is not yet clear. Meanwhile, recent debates over AI regulation have led to calls for “evidence-based AI policy” which emphasize holding regulatory action to a high evidentiary standard. Evidence is of irreplaceable value to policymaking. However, holding regulatory action to too high an evidentiary standard can lead to systematic neglect of certain risks. In historical policy debates (e.g., over tobacco ca. 1965 and fossil fuels ca. 1990) “evidence-based policy” rhetoric is also a well-precedented strategy to downplay the urgency of action, delay regulation, and protect industry interests. Here, we argue that if the goal is evidence-based AI policy, the first regulatory objective must be to actively facilitate the process of identifying, studying, and deliberating about AI risks. We discuss a set of 16 regulatory goals to facilitate this and show that the EU, UK, USA, Brazil, Canada, and China all have substantial opportunities to adopt further evidence-seeking policies.

Probabilistic Methods · Everything Else

Guoxuan Xia, Olivier Laurent, Gianni Franchi, Christos-Savvas Bouganis

Label smoothing (LS) is a popular regularisation method for training neural networks as it is effective in improving test accuracy and is simple to implement. ''Hard'' one-hot labels are ''smoothed'' by uniformly distributing probability mass to other classes, reducing overfitting. Prior work has shown that in some cases *LS can degrade selective classification (SC)* -- where the aim is to reject misclassifications using a model's uncertainty. In this work, we first demonstrate empirically across an extended range of large-scale tasks and architectures that LS *consistently* degrades SC. We then address a gap in existing knowledge, providing an *explanation* for this behaviour by analysing logit-level gradients: LS degrades the uncertainty rank ordering of correct vs incorrect predictions by regularising the max logit *more* when a prediction is likely to be correct, and *less* when it is likely to be wrong. This elucidates previously reported experimental results where strong classifiers underperform in SC. We then demonstrate the empirical effectiveness of post-hoc *logit normalisation* for recovering lost SC performance caused by LS. Furthermore, linking back to our gradient analysis, we again provide an explanation for why such normalisation is effective.

Applications · Everything Else

Matthew Fortier, Mats L. Richter, Oliver Sonnentag, Christopher Pal

Terrestrial carbon fluxes provide vital information about our biosphere's health and its capacity to absorb anthropogenic CO$_2$ emissions. The importance of predicting carbon fluxes has led to the emerging field of data-driven carbon flux modelling (DDCFM), which uses statistical techniques to predict carbon fluxes from biophysical data. However, the field lacks a standardized dataset to promote comparisons between models. To address this gap, we present CarbonSense, the first machine learning-ready dataset for DDCFM. CarbonSense integrates measured carbon fluxes, meteorological predictors, and satellite imagery from 385 locations across the globe, offering comprehensive coverage and facilitating robust model training. Additionally, we provide a baseline model using a current state-of-the-art DDCFM approach and a novel transformer based model. Our experiments illustrate the potential gains that multimodal deep learning techniques can bring to this domain. By providing these resources, we aim to lower the barrier to entry for other deep learning researchers to develop new models and drive new advances in carbon flux modelling.

Deep Learning · Everything Else

Abulhair Saparov, Srushti Ajay Pawar, Shreyas Pimpalgaonkar, Nitish Joshi, Richard Yuanzhe Pang, Vishakh Padmakumar, Seyed Mehran Kazemi, Najoung Kim, He He

Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whether this inability is due to a lack of data, insufficient model parameters, or fundamental limitations of the transformer architecture. In this work, we use the foundational graph connectivity problem as a testbed to generate effectively limitless high-coverage data to train small transformers and test whether they can learn to perform search. We find that, when given the right training distribution, the transformer is able to learn to search.We analyze the algorithm that the transformer has learned through a novel mechanistic interpretability technique that enables us to extract the computation graph from the trained model. We find that for each vertex in the input graph, transformers compute the set of vertices reachable from that vertex. Each layer then progressively expands these sets, allowing the model to search over a number of vertices exponential in the number of layers.However, we find that as the input graph size increases, the transformer has greater difficulty in learning the task. This difficulty is not resolved even as the number of parameters is increased, suggesting that increasing model scale will not lead to robust search abilities. We also find that performing search in-context (i.e., chain-of-thought) does not resolve this inability to learn to search on larger graphs.

Deep Learning · Everything Else

Murdock Aubry, Haoming Meng, Anton Sugolov, Vardan Papyan

Large Language Models (LLMs) have made significant strides in natural language processing, and a precise understanding of the internal mechanisms driving their success is essential. In this work, we analyze the trajectories of token embeddings as they pass through transformer blocks, linearizing the system along these trajectories through their Jacobian matrices. By examining the relationships between these block Jacobians, we uncover the phenomenon of **transformer block coupling** in a multitude of LLMs, characterized by the coupling of their top singular vectors across tokens and depth. Our findings reveal that coupling *positively correlates* with model performance, and that this relationship is stronger than with other hyperparameters such as parameter count, model depth, and embedding dimension. We further investigate how these properties emerge during training, observing a progressive development of coupling, increased linearity, and layer-wise exponential growth in token trajectories. Additionally, experiments with Vision Transformers (ViTs) corroborate the emergence of coupling and its relationship with generalization, reinforcing our findings in LLMs. Collectively, these insights offer a novel perspective on token interactions in transformers, opening new directions for studying their mechanisms as well as improving training and generalization.

Reinforcement Learning · Everything Else

Guangchen (Eric) Lan, Dong-Jun Han, Abolfazl Hashemi, Vaneet Aggarwal, Christopher Brinton

To improve the efficiency of reinforcement learning (RL), we propose a novel asynchronous federated reinforcement learning (FedRL) framework termed AFedPG, which constructs a global model through collaboration among $N$ agents using policy gradient (PG) updates. To address the challenge of lagged policies in asynchronous settings, we design a delay-adaptive lookahead technique *specifically for FedRL* that can effectively handle heterogeneous arrival times of policy gradients. We analyze the theoretical global convergence bound of AFedPG, and characterize the advantage of the proposed algorithm in terms of both the sample complexity and time complexity. Specifically, our AFedPG method achieves $\mathcal{O}(\frac{{\epsilon}^{-2.5}}{N})$ sample complexity for global convergence at each agent on average. Compared to the single agent setting with $\mathcal{O}(\epsilon^{-2.5})$ sample complexity, it enjoys a linear speedup with respect to the number of agents. Moreover, compared to synchronous FedPG, AFedPG improves the time complexity from $\mathcal{O}(\frac{t_{\max}}{N})$ to $\mathcal{O}({\sum_{i=1}^{N} \frac{1}{t_{i}}})^{-1}$, where $t_{i}$ denotes the time consumption in each iteration at agent $i$, and $t_{\max}$ is the largest one. The latter complexity $\mathcal{O}({\sum_{i=1}^{N} \frac{1}{t_{i}}})^{-1}$ is always smaller than the former one, and this improvement becomes significant in large-scale federated settings with heterogeneous computing powers ($t_{\max}\gg t_{\min}$). Finally, we empirically verify the improved performance of AFedPG in four widely used MuJoCo environments with varying numbers of agents. We also demonstrate the advantages of AFedPG in various computing heterogeneity scenarios.

Reinforcement Learning · Everything Else

Cevahir Koprulu, Thiago Simão, Nils Jansen, ufuk topcu

Curriculum learning aims to accelerate reinforcement learning (RL) by generating curricula, i.e., sequences of tasks of increasing difficulty. Although existing curriculum generation approaches provide benefits in sample efficiency, they overlook safety-critical settings where an RL agent must adhere to safety constraints.Thus, these approaches may generate tasks that cause RL agents to violate safety constraints during training and behave suboptimally after. We develop a safe curriculum generation approach (SCG) that aligns the objectives of constrained RL and curriculum learning: improving safety during training and boosting sample efficiency.SCG generates sequences of tasks where the RL agent can be safe and performant by initially generating tasks with minimum safety violations over high-reward ones.We empirically show that compared to the state-of-the-art curriculum learning approaches and their naively modified safe versions, SCG achieves optimal performance and the lowest amount of constraint violations during training.