Sanjiv Kumar
Hi! I work in the area of large-scale machine learning and computer vision. You can find more information about me including a complete list of papers at: www.sanjivk.com.
Authored Publications
Sort By
Preview abstract
Adaptive methods with non-diagonal preconditioning have demonstrated state-of-the-art performances on various tasks. However, the high memory cost of the existing non-diagonal preconditioning methods makes them unsuitable for the training of Low Rank Adaptions (LoRA). Additionally, these methods do not meet the criteria of efficient feature learning, which is important for LoRA optimization. In this work, we propose a non-diagonal preconditioning method to improve LoRA optimization. It has a low memory cost and achieves efficient feature learning through transformation invariance among equivalent LoRA weights. We provide theoretical justifications for our method. Our experiments on LLM LoRA finetuning demonstrate the effectiveness of our method.
View details
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Lin Chen
Aditya Menon
Forty-second International Conference on Machine Learning (2025)
Preview abstract
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal area under the ROC curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How can one synthesize such labels into a single coherent ranking? In this work, we formally analyze two approaches to this problem—loss aggregation and label aggregation—by characterizing their Bayes-optimal solutions. We show that while both approaches can yield Pareto-optimal solutions, loss aggregation can exhibit label dictatorship: one can inadvertently (and undesirably) favor one label over others. This suggests that label aggregation can be preferable to loss aggregation, which we empirically verify.
View details
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Lin Chen
Aditya Menon
2025
Preview abstract
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal area under the ROC curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How can one synthesize such labels into a single coherent ranking? In this work, we formally analyze two approaches to this problem—loss aggregation and label aggregation—by characterizing their Bayes-optimal solutions. We show that while both approaches can yield Pareto-optimal solutions, loss aggregation can exhibit label dictatorship: one can inadvertently (and undesirably) favor one label over others. This suggests that label aggregation can be preferable to loss aggregation, which we empirically verify.
View details
Preview abstract
In-context Ranking (ICR) is an emerging paradigm for Information Retrieval (IR), which leverages contextual understanding of LLMs by directly incorporating the task description, candidate documents, and the query into the model's input prompt and tasking the LLM to identify relevant document(s). While it is effective, efficiency is a significant challenge in this paradigm, especially as the candidate list grows due to quadratic/super-linear scaling of attention operation with context length. To this end, this paper first identifies inherent and exploitable structures in the attention of LLMs finetuned for ICR: (1) inter-document block sparsity: attention is dense within each document block but sparse across different documents in the context; and (2) query-document block relevance: the attention scores from certain query tokens to a document block in middle layers strongly correlate with that document's actual relevance. Motivated by these observations, we introduce BlockRank (Blockwise In-context Ranking), a novel method that adapts the attention operation in an LLM by (a) architecturally enforcing the observed inter-document block sparsity, reducing attention complexity from quadratic to linear without loss in performance, and (b) optimizing query-document block relevance for true relevant documents during fine-tuning using an auxiliary contrastive training objective, improving retrieval in attention. Experiments on BEIR, MSMarco and NQ with Mistral-7B demonstrate that BlockRank Mistral matches or outperforms existing SOTA listwise rankers and controlled fine-tuned baseline while being significantly more efficient at inference (4.7x for 100 MSMarco documents in context) and scaling gracefully to long-context shortlists, around 500 documents in-context (approximately 100K context length) within a second, presenting a scalable and effective solution for ICR.
View details
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Lin Chen
Aditya Menon
2025
Preview abstract
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal Area Under the ROC Curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How can one synthesize such labels into a single coherent ranking? In this work, we formally analyze two approaches to this problem -- loss aggregation and label aggregation -- by characterizing their Bayes-optimal solutions. We show that while both approaches can yield Pareto-optimal solutions, loss aggregation can exhibit label dictatorship: one can inadvertently (and undesirably) favor one label over others. This suggests that label aggregation can be preferable to loss aggregation, which we empirically verify.
View details
Analyzing Similarity Metrics for Data Selection for Language Model Pretraining
Dylan Sam
Afshin Rostamizadeh
Gui Citovsky
Advances in Neural Information Processing Systems (NeurIPS) (2025) (to appear)
Preview abstract
Measuring similarity between training examples is critical for curating high-quality and diverse pretraining datasets for language models. However, similarity is typically computed with a generic off-the-shelf embedding model that has been trained for tasks such as retrieval. Whether these embedding-based similarity metrics are well-suited for pretraining data selection remains largely unexplored. In this paper, we propose a new framework to assess the suitability of a similarity metric specifically for data curation in language model pretraining applications. Our framework's first evaluation criterion captures how well distances reflect generalization in pretraining loss between different training examples. Next, we use each embedding model to guide a standard diversity-based data curation algorithm and measure its utility by pretraining a language model on the selected data and evaluating downstream task performance. Finally, we evaluate the capabilities of embeddings to distinguish between examples from different data sources. With these evaluations, we demonstrate that standard off-the-shelf embedding models are not well-suited for the pretraining data curation setting, underperforming even remarkably simple embeddings that are extracted from models trained on the same pretraining corpus. Our experiments are performed on the Pile, for pretraining a 1.7B parameter language model on 200B tokens. We believe our analysis and evaluation framework serves as a foundation for the future design of embeddings that specifically reason about similarity in pretraining datasets.
View details
Better autoregressive regression with LLMs via regression-aware fine-tuning
Zhao Meng
Aditya Menon
The Thirteenth International Conference on Learning Representations (2025)
Preview abstract
Decoder-based large language models (LLMs) have proven highly versatile, with remarkable successes even on problems ostensibly removed from traditional language generation. One such example is solving regression problems, where the targets are real numbers rather than textual tokens. A common approach to use LLMs on such problems is to perform fine-tuning based on the cross-entropy loss, and use autoregressive sampling at inference time. Another approach relies on fine-tuning a separate predictive head with a suitable loss such as squared error. While each approach has had success, there has been limited study on principled ways of using decoder LLMs for regression. In this work, we compare different prior works under a unified view, and introduce regression-aware fine-tuning(RAFT), a novel approach based on the Bayes-optimal decision rule. We demonstrate how RAFT improves over established baselines on several benchmarks and model families.
View details
Faster Cascades via Speculative Decoding
Seungyeon Kim
Neha Gupta
Aditya Menon
International Conference on Learning Representations (ICLR) 2025
Preview abstract
Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches involve interleaving models of different sizes, but via fundamentally distinct mechanisms: cascades employ a deferral rule that invokes the larger model only for "hard" inputs, while speculative decoding uses speculative execution to primarily invoke the larger model in parallel verification mode. These mechanisms offer different benefits: empirically, cascades are often capable of yielding better quality than even the larger model, while theoretically, speculative decoding offers a guarantee of quality-neutrality. In this paper, we leverage the best of both these approaches by designing new speculative cascading techniques that implement their deferral rule through speculative execution. We characterize the optimal deferral rule for our speculative cascades, and employ a plug-in approximation to the optimal rule. Through experiments with T5 and Gemma models on benchmark language tasks, we show that the proposed cascading approach matches the quality of a regular cascade, but at reduced inference costs.
View details
Think before you speak: Training language models with pause tokens
Sachin Goyal
Ziwei Ji
Aditya Menon
Vaishnavh Nagarajan
International Conference on Learning Representations (ICLR) (2024)
Preview abstract
The present-day language model generates its response by producing a series of tokens in immediate succession: the $K+1$th token is an outcome of manipulating exactly $K$ hidden values in each layer corresponding to each of the $K$ previous tokens. Is it possible to somehow allow the model to manipulate more hidden values before committing to an answer? If yes, would this help? We explore these questions by training models with learnable \textit{pause} tokens. Besides feeding the usual prefix to the model, our idea is to feed the model with an additional sequence of pause tokens. On these tokens, the model's output is ignored all the way until the last pause token, where we begin extracting the answer. We explore this idea of ``delayed answering'' in a 1B model, where we consider both pre-training and/or fine-tuning with pause tokens. We find that while merely finetuning a standard model is not very helpful, pause-pretrained models shows promise on some downstream tasks such as GSM (reasoning) and Squad, CommonSenseQA and Lambada (question-answering tasks). We also conduct various ablations to explore the effect of the number of pause tokens. While our work takes a preliminary exploration in delayed computations for language models by focusing on a 1B model, we hope it inspires future work that can make this idea practically feasible without pre-training and for models trained with other pretraining objectives and other sizes.
View details
MarkovGen: Structured Prediction for Efficient Text-to-Image Generation
Sadeep Jayasumana
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)
Preview abstract
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts. However, this quality comes at significant computational cost: nearly all of these models are iterative and require running sampling multiple times with large models. This iterative process is needed to ensure that different regions of the image are not only aligned with the text prompt, but also compatible with each other. In this work, we propose a light-weight approach to achieving this compatibility between different regions of an image, using a Markov Random Field (MRF) model. We demonstrate the effectiveness of this method on top of the latent token-based Muse text-to-image model. The MRF richly encodes the compatibility among image tokens at different spatial locations to improve quality and significantly reduce the required number of Muse sampling steps. Inference with the MRF is significantly cheaper, and its parameters can be quickly learned through back-propagation by modeling MRF inference as a differentiable neural-network layer. Our full model, MarkovGen, uses this proposed MRF model to both speed up Muse by 1.5X and produce higher quality images by decreasing undesirable image artifacts.
View details
